每天知道
你的领域
出了什么

This tutorial paper provides a step-by-step, reproducible walkthrough of NeuraDock Agent, an open-source EEG agent focused on Alpha dynamics and visual cognitive-load analysis. The goal is practical: a reader should be able to install the agent, run EEG preprocessing and quality control, generate Alpha dynamics figures, perform within-subject Rest/Task visual cognitive-load comparison, run the public mini-dataset analyses and compare them with the reference validation summary, start an online dashboard, call the real-time API from an external application, and use the LLM interpretation layer to explain quality risks. Existing EEG toolkits provide excellent offline analysis, but assembling a real-time, quality-gated cognitive-load pipeline often requires manually bridging acquisition, custom QC, Alpha feature extraction, and a web API; this tutorial closes that offline-to-online gap. The tutorial uses a quality-gated workflow: downstream Alpha and workload metrics are computed only after preprocessing and QC gating rather than directly from raw EEG. In the included mini-dataset validation, the agent processed 18 recordings, generated 10 within-subject comparisons, observed task-related posterior Alpha suppression in 7 of 10 contrasts, estimated initial evidence of within-subject repeatability, and benchmarked local online API latency. The tutorial is intended for researchers, developers, and applied teams who want a transparent path from EEG files to real-time visual cognitive-load prototypes.

Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned classifiers, prompt-based steering) that offer no formal guarantees, or on hand-coded symbolic enforcement that does not scale to the breadth of real policy specifications. We present an autoformalization pipeline that translates agent prompts, MCP tool descriptions, and natural language policy documents into formally verified policies using an LLM-based generator-critic loop. The resulting policies are written in the Cedar Policy Language. On the MedAgentBench benchmark, our autoformalized policies cover substantially more of the source natural-language specification than the hand-coded symbolic enforcement in prior work.

Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suffer from a fundamental gap: they label only the root cause, not the propagation path connecting it to the observed symptom, which largely simplifies the task to naive pattern matching. To support rigorous evaluation, we introduce PAVE, a step-wise labeling protocol that leverages known interventions from fault injection to reconstruct causal propagation paths. The mechanism is forward verification: reasoning from cause to effect rather than inferring backward from symptoms. Applying PAVE yields OpenRCA 2.0 (500 instances), the first cross-system RCA benchmark with step-wise causal annotations for LLM agents. Across 11 frontier LLMs, recovering the exact root-cause set succeeds in only 20.7% of cases on average. To locate where this difficulty lies, we relax the criterion and find what we call the ungrounded diagnosis: agents identify at least one correct root-cause service in 76.0% of cases, but ground that service in a verified causal propagation path to the observed symptom in only 61.5%. Outcome-only evaluation hides this failure mode; step-wise causal ground truth is the missing piece for trustworthy LLM-based RCA agents.

The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic supervision from frontier models, leading to limited flexibility and high-cost. To address these issues, we propose ForeAgent, an agentic forensics framework for AI-generated image detection with iterative self-evolution. First, ForeAgent adopts a Perception-Verdict architecture that aggregates multi-view cues spanning semantic, spatial, and frequency-domain features, and leverages an MLLM as a verdict module to fuse these signals for a logical-grounded verdict. Second, to enable continual self-improvement, we introduce a Hindsight-Driven Self-Refining strategy following a Sampling-Reflection-Evolution paradigm. The agent performs inference rollouts on training instances. Guided by ground-truth labels as hindsight, it reflects on failure cases and low-quality reasoning trajectories to regenerate higher-quality reasoning traces. These synthesized samples are then strictly filtered through a dual-expert quality gating module. ForeAgent continuously evolves via fine-tuning on self-curated high-quality samples. Extensive experiments demonstrate that ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy (+16.41% over AIDE), and achieves 93.3% mean accuracy on AIGCDetect-Benchmark across 16 generators. In addition, external evaluation shows that ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.

The automation of scientific discovery has reached an inflection point. While AI systems now operate instruments, optimize parameters and generate hypotheses, most remain procedural: they execute workflows fixed by human designers. True autonomous science demands epistemic autonomy--the capacity to construct, challenge and revise physical explanations in response to evidence. Here we introduce AHOIS, a multi-agent AI scientist that embeds Socratic midwifery into closed-loop experimentation. A physics-critic agent interrogates hypotheses through causal questioning, constraint checking, counterexample generation and falsification-criteria formulation. We evaluate AHOIS on a real multimode-fibre optical platform, a high-dimensional system with complex wave transformations, indirect detection, environmental drift and multi-modal acquisition. Without prior encoding schemes, classifiers or speckle models, the system autonomously proposed and validated a random-interference encoding hypothesis, discovered task-adaptive sparse-measurement strategies, diagnosed distinct failure modes (encoding instability, fluorescence contamination and detector noise) and translated a published imaging protocol into an executable workflow on a non-original configuration. The discovered encoding yielded 16x16 measurements with effective rank 56.9 and classification accuracies of 76.97% on MNIST and 83.17% on Fashion-MNIST. Ablations show that Socratic interrogation improves physical consistency, hypothesis completeness, uncertainty calibration and experimental-plan validity. These results establish a route from workflow automation towards evidence-grounded, self-correcting autonomous discovery in complex physical environments.

While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowledge. We identify this challenge as the Context Gap: the mismatch between the user context and the sufficient generation context for T2I models. To bridge this gap, we propose Qwen-Image-Agent, a unified agentic framework that integrates plan, reason, search, memory and feedback in a context-centric manner. Qwen-Image-Agent treats user input as partial context and progressively constructs the generation context through Context-Aware Planning and Context Grounding. Specifically, Context-Aware Planning identifies missing context and plans how it should be acquired and used, while Context Grounding gathers this context from reason, search, memory, and feedback. To evaluate agentic image generation, we further introduce Image Agent Bench (IA-Bench), a benchmark covering four core image agent capabilities: Plan, Reason, Search, and Memory. Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance.

Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source MLLMs are cost efficient and privacy preserving compared with commercial large models, they suffer from weak planning and limited cross website generalization. To address these limitations, we introduce the planning experience exploration and utilization (PEEU) method, which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high level training data. To quantitatively analyze the generalization behaviors driving this performance, we propose the task decomposition hierarchical analysis framework (TDHAF) to systematically study compositional generalization across three task granularities: low, middle and high levels. Our analysis reveals that mastering low level atomic skills does not guarantee high level planning competence, while high level task training yields stronger OOD generalization. Experiments on real world benchmarks demonstrate PEEU's superior effectiveness: our 7B model achieves 30.6% accuracy, outperforming the much larger Qwen2.5-VL-32B model. These demonstrate constructing hindsight high level tasks and leveraging experiences is crucial for OOD planning abilities of small MLLMs.

Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes harder to enforce. An agent touches many data sources, runs multi-step workflows, keeps state across sessions, and acts with delegated permissions. Sensitive information can therefore leak not only through its final answer but through the queries it issues, the intermediate results it handles, the memory it writes, and the messages it exchanges with other agents. We survey the privacy of LLM agents from a data-centric view, organizing the field around the data an agent touches rather than by attack type, and we use data agent as shorthand for an LLM agent that works with data. Research on these risks is active but scattered across retrieval-augmented generation, text-to-SQL interfaces, agent memory, prompt injection, access control, and contextual privacy. This survey brings that work together: we taxonomize the data sources an agent touches, the privacy risks each source creates, and the governance mechanisms that address them; we map the benchmarks used to measure these risks and identify what is missing; and we set out the open problems. Two findings recur: among governance mechanisms only information-flow control covers both compositional and cross-session inference leakage, the two least-protected risks; and no benchmark drives an agent across its data surfaces under one privacy policy, the instrument the field most lacks. Our goal is a reference that situates the scattered literature and gives future work a common framing.

High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large language models (LLMs), but their development heavily relies on manual tuning by domain experts. While recent advances in LLM-based approaches show promise for automating kernel generation, they still struggle to achieve both correctness and high performance. This limitation primarily arises from the lack of domain-specific optimization guidance, hindering effective exploration of the optimization space. We propose EGG, an Expert-Guided Agent Framework for Kernel Generation, which incorporates expert optimization principles to guide LLMs' decisions. Inspired by expert workflows, we decompose kernel generation into two hierarchical stages: 1) algorithmic structure design, which establishes a high-quality computational structure foundation; 2) hardware-specific tuning, which performs targeted adjustments through parallel mapping, tensor tiling, and memory optimization. This staged decomposition defines explicit optimization objectives, structuring the design space to achieve progressive refinement. To this end, a stage-aware multi-agent collaboration mechanism is designed for inter and intra-stage context management, ensuring stable optimization trajectories. Experiments on KernelBench and real-world workloads show that EGG achieves a 2.13x average speedup over PyTorch, outperforming existing agent-based and RL-based approaches.

Building persistent embodied agents in unstructured environments demands unified orchestration of heterogeneous tools spanning both cyber (APIs, IoT) and physical (manipulation, navigation) domains, coupled with autonomous recovery from physical failures that inevitably arise over extended operation. Existing systems treat these as separate problems: VLM-based planners lack a unified cyber-physical action space, agent frameworks accumulate unbounded context that degrades temporal coherence, and VLA policies execute open-loop without detecting their own failures. We argue that persistent autonomy requires not a monolithic model but a hierarchical asynchronous architecture with explicit separation of planning, memory, and verification. To this end, we present OmniAct, a framework integrating a multimodal semantic planner for skill routing across unified action spaces, an adaptive hierarchical memory with event-boundary-driven compression for sub-linear context growth, and an asynchronous visual preemption engine that closes the semantic loop during physical execution. Across 40 real-world long-horizon tasks on two robotic platforms coordinating four IoT devices, OmniAct achieves consistent improvements in end-to-end success across all complexity levels, maintains near-flat token consumption over under 100k+ accumulated interaction tokens, and elevates mid-scale open-weight models to proprietary-level performance.

Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations). This is a syntactic kill-switch: it is blind to whether the answer is still improving, so it over-spends tokens on easy inputs and truncates hard ones. We study semantic early-stopping: the loop halts when consecutive draft embeddings stop changing in meaning (cosine distance with a patience window) and the answer's measured quality stops improving. Our work makes three contributions. First, an honest theoretical footing: we prove deterministic termination and well-definedness and machine-check these claims, while treating the convergence of the distance sequence as an empirically tested conjecture rather than a (previously over-claimed) Banach contraction. Second, a judge-efficient evaluation protocol: we generate each question's full trajectory once, replay every stopping policy over the identical drafts, and cache every LLM-judge call, yielding a strictly paired efficiency-versus-quality comparison at low cost; we further separate operational tokens (charged to a policy) from evaluation tokens (a measurement instrument). Third, an empirical study on multi-hop retrieval-augmented question answering (HotpotQA). On the 60-question test split, a judge-free semantic stopper reduces operational tokens by 38% relative to max_iterations at parity quality (Delta-IS = -0.004, p = 0.81), whereas the full quality-gated variant is counter-productive because its per-round judging dominates cost. An oracle that selects the best round attains +0.115 Information Score over every practical policy (p ~ 4e-11), reframing the problem from "when to stop" (easy) to "which round is best" (open).

Large language model (LLM) agents enable natural language interaction for scientific visualization (SciVis). Still, prior systems have essentially prioritized autonomy over human analytical control, thereby limiting transparency and human oversight. We present HiLSVA, a human-in-the-loop agentic system that supports mixed-initiative SciVis workflows. HiLSVA integrates a plan-first multi-agent architecture with explicit human oversight, stepwise provenance tracking, and learn-at-test-time adaptation from user feedback. The system supports fluid handoff between humans and agents through both natural language and direct manipulation of visualizations, while sandboxed execution ensures safe, reproducible workflows. In doing so, HiLSVA reframes agentic SciVis as a collaborative process that augments, rather than replaces, human analytical reasoning. We evaluate HiLSVA through representative case studies and a controlled user study with twelve participants of varying expertise across multiple autonomy settings. Results show that mixed-initiative interaction improves task completion, user control, and workflow transparency across different levels of user expertise, while revealing a tradeoff between execution efficiency and human oversight. These findings highlight the importance of human-centered design in agentic SciVis and guide the development of future collaborative visualization systems. We encourage readers to explore our demo video, case studies, and source code at https://hilsva.github.io/.

Generalized sparse matrix-matrix multiplication (SpGEMM) is critical in many domains. Existing CPUs and GPUs, as well as specialized accelerators, rely on static dataflows (e.g., inner product, outer product, Gustavson, etc.). Each static dataflow sacrifices some data reuse opportunities and imposes constraints on load balance. To address this inefficiency, we extend the typical SpGEMM dataflows by considering dynamism. Specifically, we add fine-grained dynamic scheduling to optimize reuse and reduce resource contention. We also develop dynamic remapping of partially completed work to improve load balance and parallelism. These ideas are formalized into a specific dataflow called Segment. To demonstrate Segment, we codesign a SpGEMM accelerator called SegFold. SegFold includes a memory controller that identifies fine-grained reuse opportunities in a local window of the stationary input array and exploits them through dynamic work assignment. It also incorporates a merge network that routes inputs to appropriate processing elements (PEs) for computation while dynamically remapping the work assigned to each PE to balance load. Across diverse densities and matrix sizes, SegFold achieves a geometric-mean $1.95\times$ speedup over state-of-the-art SpGEMM accelerators and $5.3\times$ over the best static dataflow configuration, demonstrating that adding dynamism to the dataflow design space unlocks reuse and load-balance gains that no static scheduling choice can achieve in isolation.

Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and achieving the low latency required for real-time interactive scenarios. Meanwhile, recent streaming video generation methods are mostly developed for synthesis and cannot be directly applied to editing due to the strict preservation requirement and region-specific control. In this work, we present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness. Our key design is a three-stage distillation pipeline that progressively transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor, enabling stable long-horizon edits without sacrificing visual fidelity. To further support real-time deployment, we introduce an AR-oriented mask cache that reuses region-related computation across frames, substantially reducing redundant processing and accelerating inference. Finally, we establish a dedicated benchmark for streaming video editing. Extensive evaluations demonstrate that our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications.

Cloud database systems cannot rely on instance-local disks for write-ahead logging (WAL) durability, forcing WAL onto remote storage. Existing options are unsatisfying: remote block storage like EBS is easy to adopt but adds substantial write latency and cost, while object storage offers excellent durability and low storage cost but is impractical for OLTP due to high latency and per-append cost. Many cloud-native databases, therefore, depend on purpose-built logging backends, which are typically proprietary and tightly coupled to engine-specific replication and recovery protocols, limiting reuse. We present BtrLog, a reusable cloud logging service that combines low-latency durable appends with low-cost archival for the common single-writer architecture. BtrLog replicates log records across a quorum of SSD-backed log nodes in a single network round trip, reducing sensitivity to stragglers in commit latency. To minimize storage cost, log nodes archive records to object storage as large segments, which are written asynchronously and off the latency-critical write path. In our evaluation, BtrLog achieves lower latency than EBS and enables higher end-to-end transaction throughput when integrated into a DBMS.

Modern edge computing applications, particularly high-throughput stream processing like Vision Transformers (ViTs), demand massive spatial parallelism and efficient data movement under tight power and area constraints. Coarse-Grained Reconfigurable Architectures (CGRAs) offer a promising paradigm to balance performance, flexibility, and energy efficiency. This paper analyzes the impact of two critical CGRA design choices: processing element heterogeneity and local data reuse support. We evaluate essential computational kernels (Fast Fourier Transform (FFT) and General Matrix Multiply (GEMM)) alongside an end-to-end seizure detection transformer workload across two distinct configurations: a baseline homogeneous architecture and a heterogeneous evolution integrating specialized functional units with an Scratchpad Memory (SPM). Our evaluation demonstrates that the SPM significantly optimizes data movement, reducing memory traffic eightfold compared to a memory-less design. While the heterogeneous architecture achieves superior energy efficiency for data-shuffling tasks, the homogeneous design minimizes area overhead by 4.4x to 8.2x relative to state-of-the-art CGRAs. Furthermore, it sustains a 700 MHz operating frequency, enabling up to a 5x execution speedup over the heterogeneous configuration during matrix computations. Ultimately, this work provides an architectural roadmap for selecting CGRA fabrics based on the arithmetic intensity, performance goals, and resource envelopes of edge-scale workloads.

Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value. We present two efficiency methods that exploit this asymmetry. CascadeFormer tapers width with depth to match the uneven information flow across layers, achieving comparable perplexity to a uniform baseline at the same training budget while reducing latency by 8.6% and increasing throughput by 9.4%. CascadeFlow Pruning removes layers using accumulated training gradients, with no post hoc analysis. It outperforms standard heuristics on perplexity and rank-stability and stays competitive on downstream accuracy. To motivate these methods, we propose Gradient Fan-in Asymmetry (GFA) as a structural account of why deeper layers contribute less. In Pre-LayerNorm residual stacks, the gradient at a layer is the sum of an identity path and all downstream functional paths, producing a gradient fan-in that decays linearly with depth (and quadratically under deep supervision), yielding richer gradients for early layers and sparser ones for later layers. We provide correlational and interventional evidence for GFA on models trained from scratch up to 1.2B parameters. Across Transformers and ResNets, accumulated training gradients follow the theoretical fan-in and are associated with post hoc layer importance. Two interventions point to structure rather than magnitude as the bottleneck: equalizing per-layer gradient norms does not restore late-layer value, while increasing downstream path counts via parameter-shared repetition restores and elevates it. Whether gradient magnitude proxies fan-in beyond high-rank regimes, and how these dynamics behave at the 100B+ scale, remain open questions.

Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features. However, training SAEs is computationally expensive, and available open-source SAE models remain limited. In this work, we introduce Qwen3-Instruct SAE, a comprehensive suite of SAEs trained on the Qwen3 instruction-tuned model family, covering Qwen3-1.7B, Qwen3-4B, and Qwen3-8B. For Qwen3-1.7B and Qwen3-4B, we train layer-wise SAEs at three key activation sites: residual streams, MLP outputs, and attention outputs. For Qwen3-8B, we train SAEs on a subset of residual stream layers. We systematically evaluate these SAEs using both activation-level reconstruction metrics and model-level recovery metrics, revealing distinct sparsity--fidelity trade-offs across layers and components. Finally, we demonstrate the utility of Qwen3-Instruct SAE through a refusal-steering case study, showing that selected SAE features can causally steer instruction-tuned Qwen3 models toward refusal behavior. Our release provides a practical resource for studying sparse representations, feature-level mechanisms, and behavioral interventions in instruction-tuned language models

Modern compilers are complex software systems that must correctly translate high-level programming languages into machine code across multiple architectures. Cranelift, a fast and modern compiler backend originally developed for WebAssembly and recently adopted as an experimental backend for Rust, has gained increasing importance due to its superior compilation speed compared to LLVM and comprehensive multi-architecture support, including x86-64, AArch64, s390x, and RISCV64. However, despite decades of development in compiler testing, testing Cranelift still presents unique challenges, including (1) constructing valid IR under the strict enforcement of SSA form, (2) generating sequences with sufficient computational density to stress backend components, and (3) balancing broad backend coverage with efficient root cause analysis across heterogeneous architectures. To address these challenges, we propose CLIR, a differential testing framework that integrates a syntax-preserving hierarchical generation strategy to guarantee SSA validity, a liveness-guided instruction refinement mechanism to maximize computational density, and a diagnosis-guided cross-architecture adaptation scheme to facilitate efficient root cause analysis across heterogeneous backends. Our comprehensive evaluation demonstrates that CLIR significantly outperforms existing state-of-the-art baselines, detecting 8x, 24x, and 8x more unique bugs than cranelift-fuzzgen, wasm-smith, and WASMaker, respectively, while RustSmith uncovered no bugs. Consequently, within 72 hours of testing, CLIR discovered 24 bugs spanning all target architectures, with 21 confirmed and 9 fixed.

Warm-started diffusion samplers accelerate iterative inference, but it is rarely clear which part of the pipeline carries the gain. We study retrieval-warmed energy-based reasoning (RW-EBR) — an IRED energy-based diffusion model \cite{du2024ired} augmented with a Modern Hopfield trajectory memory — and contribute a five-arm ablation methodology (oracle, best-constant, per-query-random, shuffled, aligned) that separates three confounded effects: class-prior bias shift, stochastic warm-starting, and graph-aligned value reuse. The diagnostic decomposition is adapted from LLM-RAG evaluation \cite{ru2024ragchecker}. On connectivity-2 (Erdős--Rényi all-pairs reachability), the aligned-vs-shuffled-oracle swing reaches $+35$\,pp balanced accuracy on a fixed 1{,}000-graph validation-set diagnostic, with value distribution and retrieval mechanics fixed, only per-graph alignment destroyed, while per-query random initialisation falls below cold — per-graph alignment, not bias shift or stochasticity, dominates. Yet the deployable cold-prediction pipeline misses the acceptance gate at stored-value quality. The same diagnostic logic, stopped at the key-quality screen, applied to Sudoku with a task-specific key encoder produces a clean negative at a different component — key quality, under the current setup. The decomposition names the first blocking component on each task. The setting — graph reachability refined by an iterative diffusion sampler, with explainability of failure modes as the lens — places the work within structured and spatio-temporal reasoning.

We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Multi-Token Prediction (MTP) module on initial token drafting, its draft accuracy degrades sharply at later positions, as error accumulation from unverified intermediate tokens harms draft acceptance rates. Although the original DFlash method supports efficient one-pass block drafting, it cannot be seamlessly adapted to the HC paradigm, since DeepSeek-V4's multi-path residual stream induces inherent feature misalignment with conventional drafting designs. To resolve this architectural mismatch, we propose two dedicated, model-aligned optimizations for HC residual streams. First, we adopt pre-collapse residual states as the exclusive conditioning signal, preserving complete multi-path structural information and better aligning the drafter with the target's native prediction pathway. Second, we replace the heavy generic linear compressor with a lightweight gated residual reducer, whose parameters are directly inherited from the target model's built-in hc_head module. This design yields input-aware path aggregation with three orders of magnitude fewer parameters while maintaining precise architectural alignment. We further enhance model training via a targeted KL distillation loss applied to the LM-head, regularizing predictions against the target distribution to improve early draft quality. Extensive experiments across math reasoning, code synthesis, and conversational benchmarks demonstrate that HyperDFlash consistently outperforms both the native MTP baseline and vanilla DFlash adaptation, achieving substantial gains in average accepted draft length and decoding speedup. These results validate HC alignment, gated reduction, and targeted distillation for high-performance speculative decoding.

Apple silicon exposes unified CPU-GPU memory, but the cache state left after a completed GPU command is not documented. This paper characterizes that phase boundary on a 14-core Apple M4 Pro. We validate the measurement pipeline against unmodified STREAM 5.10 and BabelStream 5.0, then adapt an 8192-byte system-level-cache occupancy pattern to a synchronized Metal experiment. A GPU kernel touches 0 to 512 MiB and finishes before a 16 MiB CPU probe begins. The first CPU traversal is slower after large GPU footprints, while a second traversal removes most of the cost, showing residual shared-cache displacement rather than simultaneous DRAM contention. A separate matched-block experiment measures GPU slowdown under high-priority CPU traffic and finds background QoS close to baseline. Root PMU measurements and public IOReport histograms provide hardware grounding: they distinguish L1D refill sectors from software cache-line size, expose page-offset-dependent conflict behavior, and separate performance-core, efficiency-core, and AGX demand. The results identify a reproducible post-GPU cache-displacement window on M4 Pro and quantify a simple one-pass software recovery mechanism.

As Moore's law reaches its physical and economic limits, domain-specific approaches are increasingly employed to accelerate machine learning workloads. Hyperdimensional Computing (HDC) represents one such emerging paradigm, offering an alternative to conventional deep learning techniques. Rooted in cognitive models of computation, HDC is designed bottom-up with hardware efficiency as a first-class objective. HDC workloads map naturally to heterogeneous hardware platforms, including CPUs, GPUs, and FPGAs, as well as emerging in-memory computing technologies such as Resistive RAM (ReRAM) and Phase-Change Memory (PCM). HDC algorithms are intrinsically tolerant to noise and approximation, enabling substantial performance gains with minimal accuracy loss. In this work, we introduce ApproxHDC, a framework for automated identification and application of domain-specific approximations in HDC workloads. ApproxHDC extends the HPVM-HDC compiler infrastructure to enable retargetable compilation across diverse hardware backends, including CPUs, GPUs, and simulated ReRAM and PCM-based accelerators. The space of possible approximations is exponentially large; ApproxHDC employs efficient search and analysis to navigate it and identify high-impact configurations spanning both software and hardware levels.

The adoption of powerful diffusion models is hindered by their significant inference latency. Recent ``cache-then-forecast'' schemes alleviate this issue by accelerating DiTs using derivative-based polynomials, but they suffer from severe quality degradation at high acceleration ratios. Our analysis reveals its root cause: the discrete extrapolation performed on representations that are misaligned with the continuous diffusion trajectory and are numerically unstable. Thus, accelerated DiTs suffer from accumulated spatial errors, noisy derivative amplification, and high-order instability. We therefore reformulate accelerated inference as stable macro-trajectory extrapolation in ordinary differential equation (ODE) space. Instead of predicting intermediate features, we align forecasting with the model's Global Drift (GD), i.e., the end-to-end state evolution, thereby eliminating feature inconsistency and memory overhead. However, even this smooth macro-trajectory remains vulnerable to the derivative fallacy: its higher-order temporal derivatives are intrinsically noisy. Thus, we introduce a derivative-free barycentric Lagrange extrapolator to effectively bypass derivative instability and approximation error. We further propose a bounded Phase Mapping that regularizes the extrapolation domain, suppressing oscillatory error growth. These elements collectively constitute ResilPhase, a noise-resilient acceleration framework. Experiments on FLUX.1-dev and HunyuanVideo demonstrate state-of-the-art fidelity under aggressive acceleration ratios.

Language Models (LLMs) are powerful toolsand have been increasingly adopted for complex software engineering tasks. As the number of parameters increases, results can often be improved, but this also imposes substantialmemory requirements. While quantization effectively reduces thememory footprint, its overall impact is often summarized onlyby benchmark scores, which mask changes in model behaviorand non-functional overheads. In this work, we conduct anempirical evaluation of LLM quantization using AutomatedProgram Repair (APR), a complex task in software engineering.We analyze 13 quantization configurations spanning differentbit-widths, methods, and target components (weights and KVcache) across six representative LLMs, evaluated on two APRbenchmarks (HumanEval-Java and Defects4J). Our findings reveal that base and quantized models can provide different sets of repaired problems with little overlap, whileretaining a comparable number of repaired problems. Althoughquantization successfully reduces memory footprints by up to85%, it increases both inference time and energy consumption,which we attribute to suboptimal hardware utilization. OurPareto trade-off analysis shows that 48% of the configurationsevaluated are strictly dominated by alternatives. Rather thanidentifying a superior quantization method, our findings highlightthat the trade-offs between effectiveness, memory footprint,and energy efficiency are sensitive to the underlying modelarchitecture and the complexity of the task.

In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes. It has two key components, learnable modulation (LM) and softened ternarization (ST), which are coupled from an optimization perspective. LM leverages a composition of learnable factors to modulate the distribution of pre-trained high-precision weights and the ternary threshold, making them less sensitive to ternarization. ST further introduces a differentiable transition function to guide the ternarization process toward stable convergence. We show that, for pre-trained LLMs with 1.7B to 8B parameters, CAT-Q can efficiently quantize them into ternary models using only 512 calibration samples, while achieving superior performance than the seminal BitNet 1.58-bit v1 and v2 families (with 1.3B to 7B parameters) trained with 100B tokens, yielding about a 100,000X reduction in training tokens. Moreover, we show for the first time that CAT-Q can quantize much larger pre-trained LLMs having 14B to 235B parameters into leading ternary models within just 8 to 60 hours on 8 A100-80GB GPUs. Code is available at https://github.com/IntelChina-AI/BitTern.

Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state. Deploying these models on edge hardware requires significant compression, but unlike conventional sequence models, quantization errors compound across recursive reasoning cycles rather than across output tokens. As a result, standard intuitions about compression fail to apply. In this work, we ask what survives when recursive reasoners are compressed. Across a full precision sweep, three tasks, and two recursive architectures, we find that aggressive compression preserves local prediction but destroys global reasoning: cell accuracy holds while puzzle-exact accuracy collapses to zero under naive INT4 pruning, distillation, and linear attention alike. Token-level objectives, including quantization-aware training, cannot repair it. The collapse is architectural — it strikes MLP-mixing recursion but not attention on the same task — and we reverse it with per-channel calibrated INT4 without retraining. We also introduce carry-trajectory fidelity, the cosine similarity to the full-precision reasoning path, as a label-free signal that predicts this damage and its recovery before a task evaluation. The combined result is a deployment recipe: flash-streamed embeddings remove a 99.4MB bottleneck, INT8 at one cycle matches full-depth accuracy at 6x fewer FLOPs (8MB SoC), and calibrated INT4 fits a 4MB microcontroller.

Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importance estimation, and their cross-architecture behavior remains unpredictable. This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order, with lightweight low-rank recovery between stages to re-estimate component importance. An information-theoretic analysis motivates this ordering, and the Structural Independence Assumption (SIA) is formalized as a checkable condition predicting whether per-component pruning criteria are reliable for a given architecture: Multi-Head Attention (MHA)+GELU designs satisfy the SIA, whereas Grouped Query Attention (GQA)+SwiGLU designs violate it. On bearing fault diagnosis spanning 88M to 6.25B-parameter models, the framework extends achievable compression to 13.8 times on MHA+GELU architectures with 83.82% accuracy (+3.70 percentage points (pp) over the strongest baseline), while exposing a ~74pp accuracy collapse on GQA+SwiGLU architectures that violate the SIA. Deployed on an industrial slewing bearing fault diagnosis platform with NVIDIA DGX Spark, compressed models reduce inference latency by up to 67.2% and peak memory by 62.5%, demonstrating viability for IIoT edge inference.

Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that represents far history as a fixed-capacity summary state rather than retaining token instances. ProtoKV keeps an exact near-window KV cache and aggregates older content into a semantic-spatial prototype bank with residual statistics. At query time, each prototype is exposed through a bounded pseudo-token interface that is drop-in compatible with standard attention. Under matched budgets and comparable query-time cost, ProtoKV improves accuracy by up to 12.5 points over token-retention baselines on SVU benchmarks in the long-delay regime, with gains that grow as query delay increases.

Interleaved multimodal reasoning improves visual grounding by revisiting visual evidence during multi-step generation, yet existing methods typically rely on token replay, repeatedly forwarding selected visual tokens. A natural shortcut is to reuse the historical visual key-value (KV) cache directly. However, we identify a critical failure mode of this strategy: cached visual keys are already bound to their original positional context. Such stale positional binding distorts attention under later decoding contexts and can trigger severe autoregressive decoding collapse. This failure suggests that effective cache reuse requires reconstructing visual evidence under positions compatible with the current decoding state, rather than directly copying position-bound historical cache entries. To this end, we propose Position Rebinding Cache Reuse (PRCR), a cache-level framework for replay-free visual revisiting. PRCR stores raw visual KV cache together with their original spatial coordinates, then reassigns position-compatible coordinates to select entries and rebinds their keys before injecting the reconstructed cache into the active decoder cache. This design reuses historical visual evidence while preserving textual positional continuity and relative visual structure. Experiments across multiple multimodal reasoning benchmarks show that PRCR achieves replay-level or better performance, improving average accuracy by 5 percent and reducing visual-revisiting computation by up to tens of thousands of times.