Searcharxiv⌕ Search

arXiv subjects

Baochang Zhang

Publications and source records attributed to Baochang Zhang.

At least 19 recordsLinked to original sources

FAVR: Flow-Aware Visual Residual Alignment for Vision-Language-Action Policies

Pretrained video representations provide rich temporal information for robotic manipulation, yet effectively integrating them into existing vision-language-action (VLA) policies remains challenging. We present Flow-Aware Visual Residual Alignment (FAVR), a lightweight framework for flow-aware visual conditioning of frozen VLA policies. FAVR maintains a compact temporal visual state through linear Test-Time Training (TTT) and retrieves action-conditioned visual features throughout flow-based action generation. By exploiting the affine structure of the frozen action head, we explicitly characterize how injected visual features influence predicted action velocities and formulate flow-aware channel selection as a box-constrained optimization problem. We develop a FISTA-based solver for joint gate optimization and derive an efficient closed-form approximation through diagonalization and rescaling. With only 1.74-2.19M trainable parameters and 5,000 adaptation steps, FAVR improves pretrained VLA policies across benchmarks. On RoboTwin 2.0, FAVR improves LingBot-VLA from 87.12% to 90.04% under clean conditions and from 86.88% to 89.38% under randomized conditions. A controlled ablation on five RoboTwin tasks further shows that flow-aware gating increases average success from 72.0% with a gate shared across flow steps to 82.0%, demonstrating the benefit of adapting visual conditioning throughout action generation.

cs.CV↗

Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding

Block drafters such as DFlash draft a block of future tokens in one forward pass, and draft trees such as DDTree verify the prefixes ranked highest by the product of the drafter's per-position distributions. Under tree verification, the expected number of accepted tokens is the probability mass the tree covers. We show that a product misallocates it: when the continuation can follow several futures, it splices them into chimeras, prefixes stitched together from different futures that the target never produces, and gives them as much budget as the futures themselves. Barring ties, no product-ranked tree can hold two futures that disagree in $m$ positions without $2^{m-1}-1$ chimeras, however well the drafter is trained, and in practice chimeras make up 27-33% of a 64-node tree. We propose Multi-Future Drafting (MFD), which restores the coupling with a latent variable instead of the chain rule: $K$ learned mode embeddings at the drafter's input draft $K$ coherent blocks in the same pass, and a mixture DDTree lets the verifier pick the future the target takes, losslessly and with $K+1$ extra vectors. On four Qwen targets from 4B to 27B parameters, at batch size 1, MFD reaches up to 7.8$\times$ speedup, 5-8% faster than the best single-mode tree trained identically and, on Qwen3-4B and Qwen3-8B, 9-16% faster than the released DARTree trained on the same prompts.

cs.AI↗

Bilateral Sharpness-Aware Minimization for Flatter Minima

Sharpness-Aware Minimization (SAM) enhances generalization by reducing a Max-Sharpness (MaxS). Despite the practical success, we empirically found that the MAxS behind SAM's generalization enhancements face the "Flatness Indicator Problem" (FIP), where SAM only considers the flatness in the direction of gradient ascent, resulting in a next minimization region that is not sufficiently flat. A better Flatness Indicator (FI) would bring a better generalization of neural networks. Because SAM is a greedy search method in nature. In this paper, we propose to utilize the difference between the training loss and the minimum loss over the neighborhood surrounding the current weight, which we denote as Min-Sharpness (MinS). By merging MaxS and MinS, we created a better FI that indicates a flatter direction during the optimization. Specially, we combine this FI with SAM into the proposed Bilateral SAM (BSAM) which finds a more flatter minimum than that of SAM. The theoretical analysis proves that BSAM converges to local minima. Extensive experiments demonstrate that BSAM offers superior generalization performance and robustness compared to vanilla SAM across various tasks, i.e., classification, transfer learning, human pose estimation, and network quantization.

cs.CV↗

Self-Evolving Visual Agent via Margin Reward

Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool invocation usually relies on curated question-answer pairs or expert demonstrations at scale, which are expensive to acquire. In this study, we propose Marvo, a simple-yet-effective self-evolution approach that enables learning tool invocation from unlabeled images. Marvo consists of two agents: (1) a challenger that generates question-answer pairs from unlabeled images, and (2) a solver that learns tool invocation by solving questions through reinforcement learning. To encourage effective tool invocation, a good training question should be difficult enough to warrant tool use, yet remain within the solver's capabilities. To this end, we introduce a margin reward to the challenger, defined as solver's performance difference with and without access to tools. With the margin reward, we create an adaptive curriculum that encourages the solver to learn effective tool invocation. Across benchmarks covering agentic reasoning, visual search, mathematical, and general real-world reasoning, Marvo improves average accuracy by up to 7.1\% --- demonstrating margin reward as a preferred way to scale question complexity without human supervision.

cs.AI↗

DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models

Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redundancy or text-vision attention. However, they frequently suffer from semantic degradation due to their task-agnostic design or unreliable attention estimates. Based on our empirical analysis, we have found that this issue arises because salient tokens in shallow layers persistently suppress emerging semantic ones through numerical inertia, leading to premature discarding of signals crucial for deep reasoning. To address the aforementioned issue, from the task-oriented aspects, we first reformulate training-free pruning as a minimization of the distortion in the final task loss and derive a tractable, token-wise upper bound to serve as a surrogate objective. Specifically, this formulation inherently reveals a previously neglected inter-layer term that accounts for gradients across layers. Accordingly, for the implementation, we propose DIPrune, a rank-based framework that employs a dual importance scoring mechanism to jointly optimize intra-layer static feature saliency and inter-layer dynamic semantic evolution. Extensive experiments on LLaVA and Qwen-VL demonstrate that DIPrune consistently achieves state-of-the-art results.

cs.CV↗

Optimal Design for Active Preference Learning with Biased LLM Judges

Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the judges may deviate from those of the target human population. Even after calibration on trusted reference data, active acquisition can shift the comparison distribution and expose residual judge bias. We therefore incorporate judge deviations into the acquisition design rather than relying on a separate calibration stage. Under joint estimation, comparisons that appear highly informative about the reward may also reflect judge bias and therefore provide less information about human preferences. To address this issue, we propose Nuisance-Adjusted Optimal Design (NAOD), a comparison-selection strategy that prioritizes policy-relevant target information after nuisance adjustment and uses the Frank-Wolfe algorithm for optimization. Theoretically, we establish a sharp conditional local asymptotic minimax lower bound on policy risk and construct an estimator that attains it. We further characterize the finite-sample cost of learning the nuisance representation and show that representation error can reverse an oracle design advantage. Finally, we validate these predictions experimentally and evaluate NAOD on Chatbot Arena data across 17 judges, 15 budget configurations, and 15 random cluster-level splits. NAOD reduces the mean regret of proxy policy by 29.1% relative to a matched target-information design, outperforms existing methods, and improves human-preference prediction on held-out data.

cs.LG↗

GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container

The two-dimensional irregular knapsack problem in a fixed circular container is an important combinatorial optimization problem for maximizing material utilization in manufacturing. Conventional geometric packing solvers can produce tightly packed layouts, yet they often partition the residual space into isolated small pockets that cannot fit valuable unplaced polygons. To overcome this late-stage packing bottleneck, we propose a failure-aware large neighborhood search framework named GeoNest, driven by a graph policy trained via reinforcement learning. Specifically, we first construct neighborhoods by pairing failed target polygons with residual pockets. We then use explanatory poses to identify the placed polygons that block candidate insertions. These diagnosed blocking relations define bounded, fixed-item repair subproblems for the underlying geometric solver. Finally, the graph policy selects the most promising subproblem for execution. For evaluation, we introduce CircleNest-Bench, a benchmark comprising 2,391 load-controlled instances from four contour sources, including a held-out industrial CAD source. Experimental results demonstrate that, under the same total time budget, GeoNest improves mean utilization over a state-of-the-art standalone packing solver by about 0.9% on average across the three main test sets and by about 0.6% on the held-out industrial set.

cs.LG↗

Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and accelerate inference, but extreme compression (i.e., mean bit-width <= 2) often leads to severe performance degradation. To address this, we propose Squeeze10-LLM, effectively "squeezing" 16-bit LLMs' weights by 10 times. Specifically, Squeeze10-LLM is a staged mixed-precision post-training quantization (PTQ) framework and achieves an average of 1.6 bits per weight by quantizing 80% of the weights to 1 bit and 20% to 4 bits. We introduce Squeeze10LLM with two key innovations: Post-Binarization Activation Robustness (PBAR) and Full Information Activation Supervision (FIAS). PBAR is a refined weight significance metric that accounts for the impact of quantization on activations, improving accuracy in low-bit settings. FIAS is a strategy that preserves full activation information during quantization to mitigate cumulative error propagation across layers. Experiments on LLaMA and LLaMA2 show that Squeeze10-LLM achieves state-of-the-art performance for sub-2bit weight-only quantization, improving average accuracy from 43% to 56% on six zero-shot classification tasks--a significant boost over existing PTQ methods.

cs.LG↗

GleanVID: Complementary Token Selection for Efficient Video Large Language Models

Video Large Language Models (VideoLLMs) have achieved strong video understanding capabilities but incur substantial inference overhead due to the large number of visual tokens. Existing VideoLLM token compression methods largely rely on selection-independent scoring, overlooking cross-frame complementarity and consequently retaining redundant evidence across frames. Instead, we view video token selection as a progressive evidence accumulation process. It aims to retain visual evidence that is individually informative and collectively complementary under a limited token budget. Building on this insight, we introduce GleanVID, a training-free inference acceleration framework for VideoLLMs. Specifically, GleanVID first allocates the global token budget across frames according to temporal novelty and then selects tokens by jointly considering local representativeness and subspace complementarity, thereby preserving richer and less redundant visual evidence. Extensive experiments across diverse VideoLLMs and benchmarks demonstrate that GleanVID consistently achieves state-of-the-art performance. Notably, with only 25% of visual tokens, GleanVID preserves 98.6% of Qwen3-VL's original performance while reducing its prefill latency by 44.7%. On LLaVA-OV-7B, GleanVID at a 25% retention ratio even slightly surpasses the original model.

cs.CV↗

MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but incurs substantial costs from rollouts and policy updates. Online prompt selection improves efficiency by using per-prompt Bayesian posteriors to predict difficulty and prioritize informative prompts. However, existing methods overlook how reliably learning signals are extracted from sampled responses. In GRPO, a response's advantage depends on both its own outcome and the randomly sampled outcomes of its peers through group normalization. Our theoretical and experimental analyses show that uncertainty in group composition introduces composition noise, a non-vanishing variance component that imposes an irreducible lower bound on gradient estimation error and impairs downstream prompt selection. We propose MaPP (Marginalized Posterior-Predictive), a unified framework for data-efficient RLVR that denoises response-level advantage estimation and improves prompt selection using a shared Beta posterior. For each response, MaPP replaces the standard group-relative advantage with a composition-invariant intrinsic advantage through closed-form Beta-Binomial marginalization. The resulting posterior-predictive estimator has an error that provably diminishes as the posterior concentrates. Using the same posterior, MaPP derives an uncertainty-aware prompt selection score to improve data efficiency without additional rollout cost. Experiments on mathematics, planning, and visual geometry across five model backbones show that MaPP consistently outperforms GRPO and strong selection baselines, achieving up to +2.45 average accuracy improvement over the strongest baseline under the same rollout budget and setting a new state of the art.

cs.LG↗

Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning

Group-based reinforcement learning such as GRPO trains LLM agents by comparing rollouts sampled for each task, without a learned critic. In long-horizon settings, these rollouts revisit shared anchor states, offering cross-rollout evidence for step-level credit. Ideally, step-level credit should incorporate evidence beyond the realized suffixes observed at an anchor while aggregating alternative continuations according to their empirical frequencies. Visit-local averaging pools realized suffix returns at shared anchors and respects observed frequencies, but does not recursively propagate evidence across rollouts, whereas shortest-path estimators have global reach but allow a rarely observed route to dominate an anchor's value. We introduce Cross-Rollout Bellman Closure (CRBC), which merges each rollout group into a finite empirical process with absorbing success and failure boundaries and evaluates its behavior-policy Bellman fixed point with one linear solve. This fixed point uses the same empirical action and transition frequencies to propagate evidence through shared anchors and aggregate alternative continuations. Backing up the resulting state values through observed transitions yields action values, whose gain over the corresponding state value provides step-level credit. A corresponding finite-depth family recovers visit-local return averaging at zero depth and converges to the exact closure as depth increases. The normalized closure credit is combined with the trajectory-level group advantage for policy optimization, without additional environment rollouts. Across ALFWorld, WebShop, and Sokoban benchmarks with multiple model scales, CRBC consistently improves final performance and learning efficiency. For example, CRBC outperforms the strongest evaluated baseline by 5.59 percentage points on ALFWorld with Qwen2.5-1.5B-Instruct.

cs.LG↗

GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents

Group-based reinforcement learning (RL) has advanced large language models (LLMs) and is increasingly extending to agentic tasks, where sparse terminal rewards make step-level credit assignment essential. Existing methods assign credit from what follows an action in sampled rollouts, but do not explicitly capture its retrospective relation to the realized outcome. Hindsight credit assignment (HCA) instead attributes credit through the ratio of hindsight to behavior-policy probabilities, but estimating the hindsight distribution requires an auxiliary model or an extra pass. To address this estimation bottleneck, we propose GraphHCA, a model-free realization of HCA that eliminates explicit hindsight-distribution estimation. For terminal-goal tasks with deterministic transitions, Bayes' rule reduces the hindsight ratio to a ratio of behavior-policy success probabilities at consecutive states. Taking logs yields a state-wise success potential, whose increment across a transition provides step-level credit. GraphHCA estimates this potential from pooled rollouts through a discounted recursion on the induced transition graph, which admits a unique fixed point on any directed graph. The resulting step-level signal is combined with the trajectory-level advantage, requiring neither a learned hindsight model nor an extra forward pass and recovering GRPO when the step-level weight is zero. Among all compared baselines, GraphHCA achieves state-of-the-art results on ALFWorld and WebShop at both LLM scales, and on Sokoban with a vision-language agent. For example, on ALFWorld it improves overall success rate by up to 24.6 points over GRPO and by up to 4.7 points over the strongest step-level baseline.

cs.LG↗

MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery

Monocular 3D hand and body mesh recovery often suffers from severe occlusion and ambiguity. Traditional deterministic methods typically regress a single optimal solution, leading to overconfident predictions. In this paper, we introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection. Specifically, during exploration, based on our probabilistic formulation and entropy maximization, we propose a novel multi-hypothesis method referred to as MHE-Former. It is a Transformer-based multi-hypothesis framework, ensuring high training efficiency and label friendliness while generating plausible and diverse hypotheses. During exploitation, we propose Hypothesis Selection, a context-aware process for multiple predictions. Especially leveraging VLM's powerful visual understanding and reasoning capabilities, it allows users to choose the most plausible and desired estimate with additional evidence and natural language intent. Extensive experiments demonstrate that our framework achieves state-of-the-art performance in accuracy and diversity across multiple datasets. The user preference study further shows the practicality of our hypothesis selection process.

cs.CV↗

AcoustiTrace: When Plausible Sound Violates Physics

Recent audio-video generators can produce semantically plausible and apparently synchronized sound, yet may still violate the acoustic processes implied by visible events and environments. Existing benchmarks provide limited support for attributing such violations to particular acoustic processes and quantifying their severity. We introduce AcoustiTrace, a diagnostic benchmark that formalizes acoustic physical realism in audio-video generation. AcoustiTrace organizes text-to-audio-video (T2AV) and image-to-audio-video (I2AV) evaluation around the acoustic process, covering sound generation, propagation environment, and acoustic reception through eight dimensions grounded in measurable acoustic quantities. Based on these evaluation dimensions, we construct a large-scale dataset organized around acoustic mechanisms, comprising real-world audio-video recordings and acoustically annotated RGB-D observations, and use it to develop targeted prompt suites and validated evaluators. Experiments reveal that even leading generators still struggle with fundamental acoustic processes despite producing plausible sound events. Finally, we show that the diagnostics AcoustiTrace provides for specific acoustic relations can guide model refinement toward more physically faithful audio and open new directions for incorporating acoustic principles into training objectives, reward modeling, and candidate selection.

cs.MM↗

Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing

Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural consistency of the original motion. Existing diffusion-based approaches struggle to balance text-responsive "change" and inertial "invariance". They often rely on coarse spatial constraints and rigid uniform time assumptions, leading to spatial motion distortions and the destruction of intrinsic physical rhythms during variable-length editing. To handle these challenges, we propose Change and Invariance Motion Editing (CIME), a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions. For spatial poses, our method integrates an omni-supervised positive-negative learning mechanism comprising hierarchical retrospective feature supervision, subtle motion preservation, and triplet-based semantic alignment. For temporal rhythms, we introduce the Riemannian Non-uniform Integral Manifold Mapping (RNIMM) module, which achieves high-fidelity reproduction of physical beats in the edited text via kinematics-aware non-uniform timestamps. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that CIME achieves state-of-the-art performance in editing alignment and structural fidelity, validating the effectiveness of our unified architecture. Our source codes and models have been released at: github.com/ZhenwuShi/CIME.git

cs.CV↗

RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification

Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approaches typically predict scene-level accidents, infer risk objects indirectly from ego behavior, or apply geometric checks after trajectory forecasting, without directly using predicted ego--object relations for risk-source localization. We propose RiskWorld, an object-centric latent world model that identifies risk from the imagined evolution of each candidate relative to the ego vehicle. RiskWorld combines pretrained predictive video representations with structured ego--object histories, contextualizes observed interactions, and rolls relation-aware object states into the future using RSSM-style latent dynamics. It decodes the rollout into object-level risk scores, supported by auxiliary future-relation and temporal-risk predictions. Inference uses only observations up to the current time, while logged futures provide training supervision. On RiskBench, RiskWorld achieves the best overall F1 of 63.0\% and the lowest false-alarm rate of 2.1\%. Further analyses show that the learned rollout captures the evolution of object-level risk before critical events, while RiskWorld's selections preserve planning-critical information under filtered observation.

cs.RO↗

Contextual Information Policy Optimization for Search Agents

Search agents extend large language models beyond static parametric memory by enabling them to acquire and use external evidence during multi-step reasoning. For knowledge-intensive tasks involving complex or evolving information, their reliability depends not only on retrieving relevant evidence but also on using it to guide subsequent reasoning. However, existing methods primarily reward final-answer correctness or intermediate progress, without directly assessing whether post-retrieval actions are grounded in the retrieved evidence. This misalignment encourages prior-driven reasoning: agents form conclusions based on internal knowledge and use retrieval mainly to confirm them, resulting in confirmation bias and inefficient evidence use. To address this issue, we propose Contextual Information Policy Optimization (CIPO), an evidence-oriented reinforcement learning framework that explicitly aligns policy optimization with external evidence use. CIPO assigns dense, turn-level credit to reasoning actions influenced by retrieved information, while combining this evidence-use signal with a global outcome reward to preserve answer correctness. With this manner, CIPO discourages evidence-detached guesses and promotes reasoning trajectories in which retrieved facts can guide or revise subsequent reasoning. Importantly, CIPO requires neither human process annotations nor an additional reward model. Extensive experiments on seven in-domain and out-of-domain benchmarks show that CIPO reduces the prevalence of prior-driven reasoning and achieves excellent performance on most tasks.

cs.AI↗

CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM

Simultaneous localization and mapping (SLAM) based on Neural Radiance Fields (NeRF) enables dense, continuous scene reconstruction. However, existing systems operating with limited online resources struggle to simultaneously construct two types of constraints, namely, compact yet discriminative spatial constraints derived from scene representations and persistent temporal constraints derived from historical observations. To address this challenge, we propose CHOW-SLAM, a dense RGB-D SLAM framework that explicitly constructs these complementary spatial and temporal constraints. Spatially, we propose a compact parametric-hash (P-H) hybrid representation that organizes components based on planes and grids across scales in P and H branches. A unified multi-output decoder further aligns the ray termination distributions induced by TSDF and density, preserving geometry and appearance under a compact parameter budget. Temporally, we propose a complementary overlap-window strategy to prevent optimization from being dominated by short-term overlap or weakly related historical observations. Within a fixed budget, the strategy retains recent frames, selects high-overlap local frames, and introduces temporally distributed historical keyframes. Loss-aware keyframe insertion and bundle adjustment scheduling further adapt optimization to tracking quality. In addition, ORB-based tracking and geometric pose estimation are used for pose initialization, followed by neural rendering optimization to improve tracking stability. Extensive evaluations on multiple datasets demonstrate that CHOW-SLAM outperforms state-of-the-art methods in both scene reconstruction quality and camera tracking accuracy. The source code is available at https://github.com/jinjidexiaohuoban/CHOW-SLAM.

cs.CV↗