每天知道
你的领域
出了什么

On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even for tokens that the student assigns low probability, but backpropagating through all token logits becomes memory-intensive for long sequences. Existing memory-saving approaches estimate corrections from sampled tokens or restrict supervision to the student's TopK tokens, introducing sampling noise or changing the full-vocabulary correction. We introduce SparseOPD, which uses full-vocabulary teacher correction to determine which corrections matter before selecting the token logits to differentiate. SparseOPD first constructs the full-vocabulary correction without retaining its backward graph, then selects tokens by correction magnitude rather than student probability. Signed residual compensation preserves the total promoting and suppressing correction mass, while correction-aware budget allocation distributes the sparse support across positions. Finally, the update backpropagates only through the selected token logits. Across six task--scale settings spanning mathematics, chemistry QA, and multimodal reasoning, SparseOPD outperforms Sampled Token and TopK in task-average accuracy and matches or exceeds Full Vocabulary. Gradient cosine similarity reaches 99% on 4B mathematics, while 8K full-parameter profiling shows 70.5% lower backward memory.

Maintaining persona consistency across multi-turn dialogues remains a core challenge for role-playing language models. Off-policy distillation from external teachers incurs distribution mismatch that compounds across dialogue turns, while reinforcement learning struggles with reward ambiguity inherent in subjective persona fidelity. We propose OSPD, an on-policy self-distillation framework where the same model serves as both teacher and student under asymmetric information: the teacher receives a complete character profile while the student sees only a brief summary, and the student generates trajectories from its own policy. We find that teacher confidence in role-playing dialogue exhibits a bimodal structure---sharply peaked at character-critical tokens yet diffuse at generic utterances---and introduce role-aware divergence switching to match this structure. A progressive trait masking curriculum further forces staged internalization of character knowledge along semantic dimensions. Experiments on CharacterBench, CharacterEval, and SocialBench show that OSPD substantially improves persona consistency over supervised fine-tuning and multi-turn RL baselines, without requiring any external teacher or reward model.

Large language models (LLMs) typically generate text autoregressively (AR), predicting one token at a time. Block diffusion language models (dLLMs) instead generate blocks sequentially while denoising multiple tokens in parallel within each block, offering a promising way to accelerate generation. Rather than training such models from scratch, recent work adapts strong pretrained AR models into block dLLMs through distillation. On-policy distillation (OPD) has been widely used for LLM training because it supervises the student on states generated by its current policy, rather than only on fixed offline trajectories. By training on the states the student actually visits, it reduces the mismatch between training and generation and can provide more relevant supervision as the student evolves. Recent work has extended this idea to AR-to-block-diffusion conversion. However, this setting introduces a fundamental mismatch in supervision: the block-diffusion student and the causal AR teacher condition on different information at the same training state. The student predicts from the entire partially denoised block, including visible future context, whereas the standard AR teacher target is defined only from the causal prefix. As a result, the teacher distribution used for distillation is not fully aligned with the information available to the student. We therefore introduce d-OPD, a future-aware on-policy distillation method that corrects the AR teacher distribution to better align with the student-visible state by incorporating visible future information within each block, providing supervision that better matches the information used by the student. Across Qwen3 models from 0.6B to 8B, d-OPD improves the six-benchmark average by up to $4.0$ points over OPDLM and reduces training time by $1.35$-$1.58\times$. The code is available at https://github.com/mit-han-lab/d-OPD.

Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, which is however often limited by repeated actions and visually similar contexts in long videos. In this paper, we study this issue from the perspective of On-policy distillation (OPD) and propose a new training regime for MLLMs termed Counterfactual Attention Policy Distillation (CAPD). In particular, OPD is a viable solution for MLLMs via providing dense teacher supervision on student-generated trajectories. But its next-token based teacher-student distillation is hard to identify the specific video segments supporting each predicted timestamp, which is critical for temporal grounding. In this case, CAPD measures how masking each temporal group changes the teacher's output distribution. The resulting counterfactual influence calibrates the teacher's attention and weights token-level distillation, allowing the student to learn the temporal evidence that affects boundary prediction. To validate CAPD, we trained it on Qwen3-VL-8B-Instruct using only 2,500 samples for one epoch, and evaluated it on the TimeLens and multiple general video benchmarks. Experimental results show that CAPD improves average recall by 12.0% relative to GRPO on TimeLens while preserving general video understanding, achieving comparable accuracy to the base model.

On-policy distillation (OPD) trains student agents through teacher supervision on their own interactions with an environment. However, in asynchronous multi-turn training, arrival-order batching can allow a few early or long rollouts to dominate learner updates while other valid rollouts become stale before being used, wasting already-generated experience. To address this problem, we introduce DivOPD, a simple learner-side batch-selection method that spreads a fixed turn budget across more rollouts and, within each rollout, prioritizes turns with larger cumulative teacher-student disagreement. Turns without usable teacher feedback are excluded. The per-turn loss and optimizer remain fixed; selection only changes which student-visited turns receive training weight. For no-progress rollouts, an optional extension briefly hands control to the teacher before returning it to the student. Across six teacher-student settings on the simulated ALFWorld, ScienceWorld, and WebShop benchmarks, with 1.5B-7B students, DivOPD raises cross-setting mean peak success rate from 77.4 to 84.4 and mean success over the last five evaluations from 71.5 to 78.6. It reaches all reported setting-specific targets with geometric-mean speedups of 1.84x in training tokens and 1.87x in learner GPU time relative to vanilla OPD. Teacher intervention further raises this last-five mean to 82.4 while retaining about 1.7x learner-GPU speedup over vanilla OPD. Code will be released at https://github.com/HanyangWang0418-oss/DivOPD.

We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the reverse-KL objective in OPD and KL-regularized policy optimization. Building on this connection, we introduce Least-Square Policy Distillation (LSPD), an RL-inspired framework that brings optimistic exploration and off-policy data reuse from value-based RL into policy distillation. LSPD preserves policy diversity through exploration while improving rollout efficiency by repeatedly learning from previously collected trajectories. Our theoretical analysis connects LSPD to optimistic value-based learning and shows that its idealized formulation achieves a sharp $\tilde{\mathcal O}(\log K)$ regret bound under online exploration. Empirically, LSPD consistently outperforms existing distillation baselines across six mathematical reasoning benchmarks and diverse teacher-student settings, with average gains of +1.59 points in Avg@16. Remarkably, through Pass@k evaluations up to k=64, we found that LSPD better preserves policy diversity by achieving stronger performance as k grows. Its fully off-policy variant achieves comparable performance to vanilla OPD using only the first 25% of rollout batches. Together, these results provide an RL perspective on OPD that offers both a principled interpretation and a practical route toward more effective and rollout-efficient language model distillation.

On-policy distillation (OPD) trains a student language model with dense feedback from a stronger teacher on student-generated trajectories. Yet standard OPD weights token-level distillation terms uniformly, implicitly treating local teacher preference as a proxy for correction utility. A decision's task value, however, depends on how the student completes the subsequent reasoning. This mismatch can cause imitation to suppress viable student strategies or reinforce paths the student cannot reliably execute. Verified trajectory outcomes provide complementary evidence about continuation quality, but do not directly identify the utility of individual decisions. We introduce Reward-Aligned Reweighting for On-Policy Distillation (R$^{2}$-OPD), which uses outcome agreement and the magnitude of teacher--student disagreement to continuously reallocate teacher supervision. It gives reward-aligned corrections greater relative influence while retaining dense feedback, moving beyond uniform imitation and hard filtering. Our analysis formalizes the mismatch between local teacher preference and student continuation value and establishes sufficient conditions for reallocation to improve first-order task progress over uniform OPD. Across seven mathematical reasoning benchmarks, R$^{2}$-OPD achieves the highest average accuracy among the compared training methods in both cross-size and same-size distillation. It outperforms standard OPD on all seven benchmarks, with average gains of 3.5 and 2.4 percentage points for 1.7B and 4B students, respectively. An extension to code generation yields an average gain of 1.6 percentage points over standard OPD. These results highlight outcome-guided supervision allocation as an effective way to translate dense teacher feedback into stronger student performance across model scales and task domains.

Sampling latency compounds in diffusion workflows, where users generate and discard many candidates before keeping one. Surprisingly, the poor outputs of standard few-step samplers do not reflect a lack of reconstruction capacity: by optimizing only the initial noise, frozen 3-4-step samplers can closely reproduce their corresponding full-step outputs. Building on this finding, we learn corrections to the initial noise and denoising updates using endpoint supervision, improving correspondence with full-step outputs generated from the same noise and prompt. The resulting previews allow users to screen candidates cheaply and reserve full-step generation for promising ones. Input correction also transfers across sampling budgets without retraining. Experiments show substantial improvements in reference fidelity, including 53-78% lower reconstruction MSE than retrained LD3 on unconditional benchmarks, alongside improved ranking preservation and candidate selection on SD1.5, SDXL, and FLUX.1-dev.

On-policy distillation (OPD) transfers knowledge between language models through teacher supervision on student-generated trajectories. With different tokenizers, a single teacher token may require multiple student tokens to generate, creating intermediate states where the event is entered but not yet completed. Existing cross-tokenizer methods align tokens or text spans to construct comparable prediction targets. We study a complementary problem after partial generation: once the student produces a prefix of a teacher token, multiple next tokens may complete the same remaining bytes, but the teacher only specifies the required completion rather than how probability should be divided among these valid continuations. We introduce Event-Set Completion Distillation (ESCD), which complements cross-tokenizer probability alignment with completion-set supervision. ESCD aggregates prefix-related teacher events and supervises the total probability of byte-compatible one-step student completions, avoiding tokenizer-dependent probability splits among individual tokens. The method reuses student trajectories and predictions, requiring neither additional rollouts nor changes to the student vocabulary. Experiments demonstrate consistent gains in mathematics, code, and scientific reasoning across model families and tokenizers, extending to large-scale MoE distillation from a 1T teacher to a 35B student. Local analyses show that retaining completion sets better matches the reference supervision, while one-step completion covers over 99% of observed compatible teacher mass after partial event entry in the studied tokenizer pairs. These findings support event entry and event completion as complementary supervision targets for cross-tokenizer knowledge transfer. Code will be released on GitHub.

Underwater image enhancement is crucial for improving visual perception in marine applications. Existing underwater image enhancement studies mainly focus on enhancement quality and visual fidelity, while rarely considering real-time deployment capability, which is essential for resource-constrained underwater robots. To this end, we introduce a physics-guided spectral distillation (PSD) method, which reduces model capacity for real-time applications while maintaining the high performance of underwater image enhancement models. To decompose the outputs of teacher and student models, PSD adopts a multilevel Haar discrete wavelet transform. It transfers low-frequency color and illumination information as well as high-frequency structural details through band-specific objectives. Moreover, the distillation process of PSD is degradation-aware. We estimate degradation-aware weights through a physical head and combine them with ground-truth-guided reliability masks to selectively retain valuable teacher guidance. Experiments on the UIEB, LSUI, and EUVP datasets validate the effectiveness of the proposed method. Furthermore, we demonstrate the benefits of enhanced images for downstream perception tasks, including object detection. Deployment on a self-developed ROV further demonstrates its practical applicability in real-world underwater scenarios.

Diffusion and flow-matching models can produce high-quality posterior samples for inverse problems, but typically require tens to thousands of network evaluations per draw. MeanFlow enables one-step generation, yet applying it to inverse problems leaves no intermediate steps at which to enforce measurement consistency. We introduce SNaP, a one-step MeanFlow posterior sampler for linear inverse problems with Gaussian noise. Its central innovation is a measurement-adapted source: a Gaussian distribution whose mean and anisotropic covariance are determined by the measurement operator, observation, and noise level. The source anchors well-measured directions while preserving variation where the measurements are weak or uninformative. We show that the exact conditional flow transports this source to the true posterior. Across natural-image restoration and multi-coil MRI, SNaP produces diverse, high-quality samples with one network evaluation per draw, 30 to 2250 $\times$ faster than iterative samplers.

Effective multi-turn agents require interaction strategies that coordinate information gathering, actions, and feedback over long horizons. GRPO is a reinforcement learning algorithm used to train these agents, but sparse trajectory-level rewards limit early exploration in small models. Recent methods augment RL with on-policy distillation (OPD) from a stronger teacher. However, a fixed mixture assumes that teacher guidance and reward optimization should retain a constant relative role throughout training and across interaction turns. This assumption can fail at two scales. Globally, as training progresses, maintaining strong distillation pressure can constrain the model from moving beyond the teacher's capabilities. Locally, teacher--student disagreement identifies where the student departs from the teacher, but cannot tell whether that departure is exploration supported by better outcomes or low-quality policy drift. Our methodological insight is that teacher guidance and reward optimization should be dynamically rebalanced over training and jointly allocated across turns. We instantiate this insight in \tide. Globally, \tide uses the measured disagreement trend as a practical schedule signal, advancing an OPD-to-RL handoff when discrepancy reduction becomes slow but remains positive and progressively increasing the relative weight of RL. Locally, \tide jointly modulates teacher-guided and reward-driven updates: relative action value and disagreement prioritize the OPD signal, whereas relative action value supplies the RL advantage and normalized disagreement reweights it across turns. Coupled with the global handoff, \tide allocates stronger teacher guidance early and gives reward-driven updates greater relative weight later in training. Experiments across multiple benchmarks, student scales, and controlled ablations support the effectiveness of TIDE's adaptive OPD--RL coordination.

World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into one visual stream and train both with the same future-video objective, despite their different visual dynamics. A stable main camera reveals scene-level task evolution, whereas wrist cameras move with the end effector, mixing local interaction changes with viewpoint shifts and self-occlusion. These contrasting predictive demands suggest that the two views may benefit from different future objectives. We introduce FutureDuet, which retains both views for control, while allowing each visual stream to receive a different future objective. For the main view, future RGB models task evolution, while interaction masks and robot skeletons focus supervision on task objects and robot motion. For the wrist stream, future latent prediction models short-horizon interaction changes without requiring pixel-level reconstruction. ActionDiT jointly reads the resulting Task State and Interaction State, combining scene-level progress with close-range interaction evidence. All auxiliary prediction modules are training-only, adding no inference overhead. FutureDuet achieves 94.2% clean and 94.1% randomized success on RoboTwin50 and 99.2% average success on LIBERO. The improvements are most pronounced on six RoboTwin50 tasks that require precise interaction, averaging gains of 9.2% and 12.8% over Fast-WAM in clean and randomized settings. Controlled studies further show complementary gains from separating the wrist pathway and designing future supervision separately for the two views.

Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally believed that training such models requires large-scale, high-quality real 3D asset data, whose acquisition remains a long-standing and challenging problem. In this work, we propose Tex-Zero, demonstrating that a high-fidelity native 3D texture generation framework can be trained without 3D assets. Our key observation is that only high-quality and fine-grained color information is essential for 3D texture training, while the required geometric information is less critical and can be manually constructed rather than obtained from real 3D assets. This finding makes it possible to transform abundant, high-quality 2D images into effective training samples for 3D texture generation. Specifically, we convert high-quality 2D images into 3D training samples by representing each image as a plane in 3D space and applying patch-wise random rotations and aggregation to construct complex geometric structures. Using these constructed image data, we train the Tex-Zero VAE, which can reconstruct real 3D assets with high quality despite never observing them during training. Building upon the Tex-Zero VAE, we train the Tex-Zero DiT also exclusively on the constructed image data, where the conditioning 2D multi-view images are transformed into planes in 3D space and also encoded by the Tex-Zero VAE, thereby reducing the representation gap and improving generation quality. Extensive experiments show that Tex-Zero generates high-fidelity 3D textures with fine-grained details solely using images as training data, offering a promising perspective on the data paradigm for scaling 3D texture generation.

Precise instruction following in image generation, such as satisfying object counts and spatial relations, remains an open challenge at least in part because it is learned using unreliable reward models such as object detectors and vision-language models. We introduce Verifiable Visual Rewards (VVR), the first framework for programmatically verifiable image rewards, and show that training on it generalizes to natural prompts. Each VVR task is a scene of geometric objects and relations among them, from which we derive both the prompt and a deterministic verifier, so tasks can be generated in any number and at any chosen complexity. We release VVRBench, with 10,000 tasks over 32 constraint types, and VVRBench-Challenge, with 720 more complex tasks; the strongest model we evaluate---GPT-Image-2.5---solves 21.4% of VVRBench-Challenge. Using VVR scores as rewards for reinforcement learning (RLVVR) raises the accuracy of Stable Diffusion 3.5 Medium on VVRBench from 2.8% to 28.3% and demonstrates consistent easy-to-hard generalization. These gains extend to out-of-domain benchmarks, and mixing VVR into existing objectives further improves overall performance and human preference, motivating the adoption of VVR into standard image generation post-training recipes.

We present SubjectAnchor, a Subject-Aware Memory-to-Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related memory construction, subject-aware temporal rotary position encoding, and memory-aware attention partition. For each target shot, the method constructs a compact memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition, memory-aware attention partition regulates the interaction between memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative memory-based and holistic baselines while maintaining competitive visual quality.

Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent diffusion-based approaches produce plausible results, but they often struggle to preserve the geometric structure and spatial coherence of foreground objects. We present GenNVS, a framework for geometry-enhanced novel view synthesis via a disentangled 3D prior. Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting and aligns them through a coarse-to-fine geometric optimization process to form a unified 3D scene. This scene conditions a video diffusion model through the proposed Dual-Stream Masking mechanism, which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping. Experimental results show that GenNVS performs favorably against recent methods in both visual quality and geometric accuracy, while naturally supporting flexible scene editing.

Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consolidates their capabilities into a single student. Existing methods, however, route each prompt to a single teacher according to its semantic category, implicitly binding the desired capability to prompt content. This coupling makes capability invocation vulnerable to prompt perturbations and prevents users from explicitly adjusting the strength of the desired capability at inference time. In this work, we introduce CapField-OPD, an OPD framework that integrates multiple teachers into a continuous capability field through explicit capability coordinates. We use teacher models as anchors to construct this field, with the coordinates determining how their outputs are combined. Each capability configuration thus receives a unique supervision target, and capability control no longer depends on prompt semantics. Since the training anchors may not be optimal at inference time, we further profile the learned field on a small calibration set. The coordinate with the highest mean reward serves as the recommended default, while coordinates that are frequently optimal offer a promising candidate set for test-time scaling. Extensive experiments on compositional generation, text rendering, and visual aesthetics demonstrate that CapField-OPD consolidates multiple specialized teachers into a single student while preserving or surpassing their performance, reliably invokes the desired capabilities under semantics-preserving prompt variations, and supports continuous capability control and coordinate-based test-time scaling.

Contemporary AI-based music generation can produce compositions that satisfy formal requirements of tonality and musical coherence. However, whether musical expression can be described by mathematical properties alone remains a fundamental question. Human composers operate within personal and cultural contexts that influence harmonic decisions and deliberate departures from established patterns. This study investigates six narrative-driven popular songs by Bob Dylan, Johnny Cash, and Ritchie Valens. Original human harmonies are compared with outputs of an explainable computational harmonizer operating on the same melodies without access to the original chord progressions. We examine harmonic vocabulary, functional persistence, repetition, non-diatonic events, and tension-resolution patterns using Chord Wheel Diagrams and BPMN-based representations. Results show that high melody-chord compatibility does not necessarily imply preservation of the original human harmonic decision pattern. Some generated harmonizations retain the economical structure of the reference, while others alter harmonic diversity or suppress distinctive events while remaining compatible with the melody. Rather than quantifying artistic quality, the study introduces narrative-conditioned harmonic structure as a complementary perspective for computational music analysis. The findings suggest that generative systems may benefit from modeling not only harmonic correctness, but also structural identity, context, and human compositional intention.

Consumer earbuds already stream inertial motion data from the head, one of the most widely worn sensor locations on the body. We ask how much of the 3D body pose a single such head IMU can recover, and whether adding more consumer sensors actually helps. We build a multimodal capture pipeline that records four-view RGB-D video together with an AirPods head IMU and two Striv insole IMUs, synchronize the streams post-hoc, and generate pseudo-ground-truth with SAM 3D Body, yielding a 35-take single-subject benchmark spanning gait, turning, vertical, everyday, and clinically inspired motions. Adapting two recurrent model families (IMUPoser and MobilePoser), we show that one head IMU recovers lower-body pose at 79.0 mm rigid-MPJPE and per-foot ground contact at 0.809 macro-F1, and that a causal variant retains most of this accuracy at streaming latency. In paired per-take significance tests across both families, adding the consumer foot IMUs never significantly improves pose and significantly degrades it in two of four model-split combinations; a mounting-bias probe and feet-only ablation identify insole orientation quality, not foot placement, as the mechanism. Extending the output to a 20-joint full-body skeleton maps the boundary: gross distal-arm motion is partially recoverable from the head alone, proximal upper-body pose is not, and staged fine-tuning recovers the leg accuracy that naive joint training sacrifices to multi-task dilution. For learned pose from consumer wearables, sensor reliability, not sensor count, is the binding constraint here. For the devices tested, the earbud is its sweet spot. Code is available at https://github.com/ZhilinGuo/one-sensor-whole-body.

A robot should be able to learn through experiments how unfamiliar objects behave and interact, then plan with that knowledge. It need not start from scratch: physics engines supply knowledge of motion and contact, but can omit entire mechanisms, such as glue curing, water heating, or wind. We present EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms. The learned programs can introduce new forces, constraints, and hidden state, and Bayesian inference estimates their parameters and states from noisy observations. The resulting model lets the agent predict the outcomes of actions, choose informative experiments, and revise its hypotheses when predictions fail. Across five simulated domains, EMPIRIC learns interpretable, reusable models, and solves more tasks with fewer environment interactions than all three baselines. On a physical robot, it learns wind forces and domino masses to solve a manipulation task. Website and code: https://yichao-liang.github.io/empiric

Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically use fixed-length chunks and either omit goal-conditioned action generation or limit their supervision to short goal spans. We introduce FlexiWorld, a JEPA-based world model that combines mixed-span goal supervision with variable-length action chunks to improve long-horizon control. During training, we sample varying goal spans and randomly partition the actions into variable-length chunks. We jointly train the world model with a causal action encoder that embeds variable-length chunks and an autoregressive actor that generates primitive actions sequentially. Student Forcing reduces exposure bias by training on generated action prefixes. For planning, Actor-Residual Cross-Entropy Method (ARCEM) combines action-residual search with within-chunk autoregressive feedback and chunk-boundary latent prediction. Across four benchmarks and goal distances, FlexiWorld with ARCEM achieves 89.29% mean success, compared with 83.98% for the strongest baseline. PushT ablations show improved direct control from mixed-span supervision, variable-length chunks, and Student Forcing. Without retraining, FlexiWorld supports different planning chunk lengths: longer chunks accelerate ARCEM by approximately $1.3\times$ on average while maintaining comparable average success.

Exo-to-egocentric video generation aims to synthesize what a person sees from their own viewpoint given third-person footage and a target head trajectory. The task requires transferring appearance and semantics across large viewpoint changes while hallucinating content never observed by the exocentric camera. Existing approaches either impose additional input requirements, such as a ground-truth initial egocentric frame or multiple synchronized exocentric views, or remain limited to category-specific settings. EgoX is the first to address cross-activity and in-the-wild generalization, but requires a human-provided caption of the non-existent egocentric view at inference and introduces a computationally expensive geometry-guided attention bias that can propagate reconstruction errors and suppress textual and visual context. We therefore propose Ego-Forge, a caption-free and bias-free framework for exo-to-egocentric generation. It introduces Dynamic Captioning, which derives conditioning tokens directly from the model's hidden states and adapts them to the diffusion timestep and network depth, replacing external text conditioning. By scaling training by an order of magnitude and using all available exocentric viewpoints, Ego-Forge learns cross-view correspondence implicitly and eliminates the need for geometry-guided attention, requiring only a lightweight depth prior. Ego-Forge achieves state-of-the-art performance on Ego-Exo4D, runs faster end-to-end, requires no external annotation at inference, and generalizes to in-the-wild scenes, including cases where over-reliance on geometry blocks appearance inference. Our model and source code will be made publicly available.

Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the planning objective is easy to optimize. We introduce Control-Geometry Straightening (CGS), a single auxiliary loss that learns planner-friendly representations by directly straightening control geometry for sampling-efficient planning. CGS matches pairwise cosine similarities among actions to those among corresponding latent differences only using local transitions from pixel-action pairs. The loss can be applied across world-model architectures using end-to-end learned or pretrained representations. Under linear-dynamics, our theoretical analysis connects this objective to temporal straightening and more balanced terminal-cost curvature across the full planning horizon, yielding finite-budget guarantees for MPPI, local contraction results for CEM, and convergence bounds for gradient descent. Across four control environments and multiple planners, CGS improves planning with fewer sampled candidates and refinement steps, achieving success-rate gains up to 20 and 12.6 percentage points over LeWorldModel (LeWM) and its temporal-straightening variant (LeWM+TS), respectively, with sampling-based planners using 128 candidates per update. Probes, comparisons with DINO-WM architecture, and planner-side ablations clarify how latent motion organization, state dependence, and dynamical context shape planning behavior. Straightening control geometry thus makes good action sequences easier to find under limited planning budgets.

Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use incoming observations as context but keep their parameters fixed, leaving conversational patterns unused as a learning signal. We introduce EvolvingAvatar, a causal generator that uses test-time training to adapt to user face video and dyadic audio during interaction. Its dyadic context prediction objective provides a self-supervised learning signal from audiovisual context without target motion labels at test time. Persistent fast weights accumulate these updates within each conversation to guide motion generation, while transient jaw adaptation responds to current audiovisual context. Predicted speech activity controls how persistent adaptation guides motion. We also introduce InterHead-Bench, a unified 455.95-hour benchmark built from single-view and dual-view conversation videos. Experiments show improved conversational motion statistics over strong baselines. On the hardest out-of-distribution split, generation improves as conversations unfold, reducing mismatch with recorded user-avatar expression statistics by up to 11.1% from the first interval.

We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures central to classical mechanics, symplectic geometry, and geometric quantization, LHFM represents each image as an exact Lagrangian graph and models its evolution through image-dependent Hamiltonian flows, which yield a transport--source parameterization of image velocities. Our primary application is deterministic video prediction: LHFM-V is a recurrent model that advances frames by integrating predicted transport and source fields, and achieves the lowest reported FLOP count among the compared recurrent models with similar prediction accuracy. The image variant, LHFM-I, shows that the same construction is compatible with flow matching: in a matched experiment, it attains a lower FID than the flow-matching baseline.

Text-to-image generative AI can produce renderings from natural-language prompts in near real time, making it increasingly popular for rapidly visualizing concepts in early-stage architectural design. Meanwhile, exchanging ideas efficiently and building shared understanding have long been central challenges in architect-client communication. How might the speed of generative image AI change this communication? To explore this question, we conducted a study with 11 architect-client pairs, in which each pair used generative image AI over video conference to collaboratively produce early-stage renderings of the client's "dream house." Our findings suggest that generative image AI helped pairs develop a solid shared understanding by providing concrete visual materials and supporting the exchange of ideas. It also shifted conversation dynamics, enabling clients to participate more actively in shaping design direction. However, challenges emerged, including a stylistic bias toward particular types of images and unpredictable shifts in design direction caused by variation across generations. We conclude with implications for the design of future generative image AI-based systems that support architect-client communication.

Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its applicability. They frequently over-personalize, applying preferences the context rules out, yet existing benchmarks score only the final response and cannot tell where this failure arises. We decompose preference handling into three stages and measure each separately: (1) knowing whether a preference applies, (2) deciding on an explicit Apply/Suppress label, and (3) generating a response consistent with that label. Using linear probes, we first show that this applicability signal remains decodable from hidden states during generation. By making the decision explicit, we then find that in most settings wrong decisions faithfully followed outnumber correct decisions lost in generation. We thus locate the failure in the decision, which breaks once the model is also asked to answer. To determine whether this reflects lost sensitivity or a response bias, we propose ABIDE (Apply-Bias Investigation via Decision-score), which adapts signal detection theory to Apply-vs-Suppress decision scores read directly from logits. ABIDE reveals a generation-induced Apply bias: merely stating an answer-generation objective shifts the decision score toward Apply while sensitivity is largely preserved, and the shift persists under controls for prompt structure, cascades across preference slots, and prompt wording. Finally, we show that subtracting a single bias scalar, estimated on a held-out split, from the decision score at decoding time reduces leakage while largely preserving fulfillment.

As image generation and editing technologies have progressed substantially, facial forgeries pose significant challenges to privacy and public safety. Due to limited ability to capture forgery cues, existing small-scale forgery detection models often struggle to generalize across various domains and unseen manipulations. To address this limitation, researchers have turned to large-scale foundation models, which can provide richer representations and better generalization. Nevertheless, relying on a single foundation model alone remains insufficient for effective forgery detection. While models like CLIP offer robust global semantic cues, they lack the capacity to capture detailed local facial features. In contrast, DINO excels at capturing local structural features of faces, but provides weaker global semantic context. To fully utilize the synergies among multiple foundation models, we propose a hierarchical multi-granular framework that integrates complementary pretrained representations. Specifically, a Global Context Branch (GCB) based on CLIP captures holistic semantic cues, while a Fine-grained Cue Branch (FCB) built on DINOv3 captures localized structural irregularities. In addition, we design a feature fusion module that enables parameter-efficient adaptation of the frozen foundation backbones by adaptively extracting and integrating complementary features from the two models. By jointly leveraging global context and fine-grained cues, our method learns more comprehensive forgery representations and achieves strong cross-manipulation performance. Extensive experiments on multiple benchmarks demonstrate the benefit of the proposed design, particularly under cross-dataset and cross-manipulation settings.

Action-conditioned video world models predict future robot interactions from multiple cameras, yet their outputs remain disparate video collections rather than a shared metric scene queryable across viewpoints and time. While existing 4D reconstruction methods offer a path to spatialize these predictions, independently reconstructing and merging each camera stream fails to enforce cross-view consistency. This limitation is particularly detrimental when combining moving robot-mounted cameras with fixed external views. To address this, we introduce RoGSW4RLD, a feed-forward framework that lifts synchronized multi-camera rollouts into a unified, time-queryable metric 4D Gaussian field. Rather than learning a separate geometric transition model, RoGSW4RLD directly reconstructs the visual future generated by existing world models. Its core innovation is a two-stage architecture: Stage 1 jointly forms the metric 4D field by fusing cross-view evidence with robot-specific articulated geometry and kinematics, while Stage 2 refines the field's geometry and appearance while strictly preserving the initial temporal displacements. Evaluated on 256 held-out DROID episodes, RoGSW4RLD significantly outperforms camera-wise reconstruction with calibrated merging, improving novel-view PSNR by 2.15 dB, reducing depth AbsRel by 47%, and lowering robot displacement error by 61%. These robust gains extend to action-conditioned Cosmos 3 rollouts, demonstrating that predicted video futures can be successfully translated into consistent, spatially queryable 4D metric representations.