Artificial Intelligence
Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation
Zhihan Zhang and Lizi Liao
Reinforcement Learning with Verifiable Rewards (RLVR) has improved the
reasoning capabilities of
Multimodal Large
Language Models (MLLMs), yet existing frameworks rely on coarse, sequence-level reward signals that lack the fine-grained supervision over the visually-grounded steps within a
multimodal reasoning chain. We investigate this gap through the lens of two
token-level metrics: visual dependency (i.e. how much a
token's prediction relies on the input image features) and predictive
entropy. Our empirical analysis reveals two key findings: (1) correct
reasoning chains exhibit a markedly sharper
entropy reduction as visual grounding intensifies, compared to incorrect ones; (2) pivotal
tokens, those whose misprediction triggers
reasoning collapse, are statistical outliers in the joint distribution of visual dependency and predictive
entropy derived from correct chains. Motivated by these findings, we propose
token-level perception-grounded advantage estimation (TPAE), which estimates
token-level advantages by measuring each
token's statistical consistency with the
vision-
entropy patterns of correct rollouts. TPAE leverages this granular score to modulate the sequence-level advantage, producing a fine-grained supervision signal that can be integrated into various RLVR frameworks. Extensive experiments on seven
benchmarks show that TPAE consistently outperforms leading strong baselines, yielding more stable and efficient optimization for
multimodal reasoning. The code is publicly available at https://github.com/Zhihan72/TPAE.
Read the full abstract ▾
Information Theory · Cross-listed from eess.SP
Deep Learning-Based Tri-Hybrid Multi-User MIMO Precoding: The Blessing of EM-Reconfigurable Antennas
Kaijun Feng, Jiaxin He, Hongrui Yu et al. (+4 more)
Electromagnetic (EM)-reconfigurable
antennas provide multiple candidate radiation patterns per element, thereby introducing an additional EM-domain degree of freedom. Integrating radiation-pattern reconfigurability, realized as EM-domain precoding, with conventional hybrid analog-digital precoding yields tri-hybrid multiple-input multiple-output (
MIMO) precoding, which can substantially improve the spectral efficiency of wideband multi-user
MIMO orthogonal frequency-division multiplexing (OFDM) systems. However, the joint design of EM, analog, and digital precoding remains challenging. To address this challenge, we propose a tri-hybrid precoding network (Tri-PNet) based on Conformer, an emerging neural architecture that combines the local modeling strength of convolutional neural networks with the global dependency modeling of
Transformers. Furthermore, two representative radiation-pattern modes, i.e., the non-regular mode and the 3rd Generation Partnership Project (3GPP) Technical Report (TR) 38.901 mode, are investigated. Tri-PNet is trained in an unsupervised manner to jointly learn EM, analog, and digital precoding by maximizing the average sum spectral efficiency. Its radiation-pattern selection network (RPSNet) employs a Conformer encoder to capture both local and global frequency-domain correlations, whereas its hybrid analog-digital precoding network (HPNet) combines cross-
attention and dual-path processing with singular-value-decomposition (SVD) and zero-forcing (ZF) priors. Simulation results under both radiation-pattern modes demonstrate that Tri-PNet outperforms random EM precoding and conventional hybrid
MIMO without EM precoding, approaches the greedy EM precoding search scheme with substantially lower online complexity, and remains robust to imperfect channel state information (CSI).
Read the full abstract ▾
All authors Kaijun Feng, Jiaxin He, Hongrui Yu, Zhen Gao, Anwen Liao, Ziwei Wan, Zhaocheng Wang
Artificial Intelligence
Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
Mingjian Gao, Zhaocheng Li, Haoyang Huang et al. (+7 more)
Persistent spatial
memory enables
embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during
navigation, making remembered locations unreliable by the time an
agent arrives. Despite advances in
memory retrieval and state prediction, accounting for continued hidden world
evolution and revising beliefs under limited visibility remain challenging. We study Evolving-World
Navigation, where
agents infer target locations from intermittent observations, predict their states at inspection time, and revise beliefs using visual evidence. We propose EvolvingNav, which constructs a time-indexed belief from timestamped 3D object histories through a structured persistence-relocation model. The belief distinguishes persistence at the last observed location from relocation to alternative locations and retains probability mass outside the known candidate set. An event-driven filter propagates the current belief as time elapses, forecasts target occupancy at candidate inspection times, and incorporates new RGB-D evidence. Negative observations downweight location hypotheses according to calibrated, visibility-conditioned detection probabilities, while evidence tracking prevents repeated use of the same observations. A frozen, zero-shot
vision-
language controller uses the updated belief to choose actions and replan. We further introduce EvoWorld-Bench, a
benchmark grounded in human activity traces, comprising 54 scenes and 803,680 tasks with controlled changes before and during
navigation. In simulation and real-
robot experiments, EvolvingNav improves
navigation success and search efficiency over the evaluated baselines. Paired experiments show the clearest gains under learnable temporal patterns, while ablations demonstrate the value of preserving uncertainty and incorporating visibility-aware evidence.
Read the full abstract ▾
All authors Mingjian Gao, Zhaocheng Li, Haoyang Huang, Wenqiao Zhang, Yingjie Niu, Hao Zhou, Chao Li, Juncheng Li, Siliang Tang, Yueting Zhuang
Machine Learning
QuanVI: Score-based Variational Inference via Quantum Maximally Mixed States
Yuchen Cong, Zerui Tao, Chao Li et al. (+2 more)
Score-based variational inference (VI) provides an alternative to Kullback–Leibler (KL)-based VI by minimizing the Fisher divergence between the variational distribution and the target. A prior score-VI approach formulates this optimization as an
eigenvalue problem, with the variational distribution constructed from low-energy eigenstates. However, this
eigenvalue-based formulation faces two high-dimensional obstacles: an intractably large parameter count due to exponential scaling and non-uniqueness of individual eigenvectors in degenerate or nearly degenerate low-energy subspaces. We propose QuanVI, a scalable
quantum-inspired
algorithm that combines a mixed-state density-operator formulation with a
quantum tensor network (QTN) parameterization using the
matrix product operator (MPO) structure. In degenerate low-energy subspaces, the density-operator formulation represents the subspace by its maximally mixed state rather than relying on a non-unique individual eigenvector, while the QTN parameterization compresses the density operator to avoid exponential parameter growth. Experiments and ablations show that QuanVI agrees with exact solutions in low dimensions and scales to high-dimensional synthetic and
Bayesian posterior-approximation
benchmarks, including challenging non-Gaussian targets.
Read the full abstract ▾
All authors Yuchen Cong, Zerui Tao, Chao Li, Zhe Sun, Qibin Zhao
Sound
Training-Free Affinity Fusion of Neural and Embedding-Based Speaker Diarization
Yehoshua Dissen, Joseph Keshet and Eduard Golshtein
Speaker diarization systems based on speaker
embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible. We introduce Training-Free Affinity Fusion (TFAF), which integrates the speaker structure inferred by a neural diarizer into an
embedding-based diarization system. The neural speaker partition is used to condition local speaker representations, from which we construct a continuous affinity
matrix and combine it with the
embedding-based acoustic affinity before a single global clustering step. The method requires no additional training, shared
embedding space, speaker-label
alignment, or hard transfer of the neural diarizer's speaker count. Experiments on AMI and CALLHOME show consistent DER improvements over both constituent systems; on AMI, fusion also improves speaker-attributed transcription. Ablations show that the neural speaker partition accounts for most of the gain, while retaining the continuous
embedding-based affinities provides additional benefit over hard partition fusion.
Read the full abstract ▾
Computer Vision
TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation
Songhe Wang, Lifu Wei, Shuolin Xu et al. (+2 more)
Video object removal presents a uniquely difficult editing challenge. Because a removal
prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this because their editing mechanisms act primarily as localized erasers. They fail to actively synthesize the missing background details and often leave behind ghosting artifacts. To solve this, we propose TripleFlow, a training-free framework that tightly couples erasure and generation. It coordinates a source flow, a residual flow, and a synthesis flow throughout the entire process. By reusing a single target prediction, the residual flow isolates and suppresses the object, while the synthesis flow independently reconstructs the occluded background. Crucially, TripleFlow injects this newly synthesized background back into the editing trajectory at every step. This continuous feedback loop ensures that the generated structures actively guide the removal process, achieving seamless completion that is spatiotemporally consistent with the unedited scene. Extensive evaluations across five challenging
benchmarks demonstrate that TripleFlow establishes a new state-of-the-art, significantly outperforming existing baselines in both reconstruction fidelity and temporal consistency.
Read the full abstract ▾
All authors Songhe Wang, Lifu Wei, Shuolin Xu, Charles A. Kamhoua, David Miller
Networking
Spatio-Temporal Wireless-Optical Planning for Multi-UAV Networks
Binglei Wang, Huiru Ao, Fan Yang et al. (+3 more)
Multi-unmanned aerial vehicle (
UAV) networks in urban low-altitude environments couple
UAV mobility, wireless access, and optical backhaul resources. Existing path-planning methods optimize flight distance or wireless signal quality, but can still concentrate traffic on shared optical backhaul links. We present Spatio-Temporal Wireless-Optical (STWO) planner, a backhaul-aware path-planning
algorithm that jointly considers flight distance, wireless link quality, and time-varying optical-link offered-load ratio. STWO updates backhaul occupancy during sequential multi-
UAV planning, allowing later
UAVs to avoid congested optical paths while maintaining wireless connectivity. Experiments show that STWO reduces peak optical-link offered-load ratio by up to 56.4% and congestion ratio by up to 72.6% under dense
UAV deployment, demonstrating the importance of wireless-optical awareness for reliable multi-
UAV transmission.
Read the full abstract ▾
All authors Binglei Wang, Huiru Ao, Fan Yang, Zhenjie Zhou, Zhonghua Peng, Jialong Li
Computation and Language
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Hanwen Liu, Yuanfu Sun and Qiaoyu Tan
Deep research tasks require
agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DAG)-based multi-
agent systems suit this setting because they support parallel execution and isolate each sub-task within a focused dependency context. Yet existing DAG-based
agents instantiate a task-level plan before execution and repair the graph only after failures or missing evidence are observed. This Plan-then-Patch strategy is brittle for deep research: the system commits most strongly when its evidence is weakest, and later revisions waste computation on branches that should not have been planned. We propose DAGent, a DAG-based multi-
agent framework with Evaluate-then-Grow incremental planning: an Orchestrator grows the task graph one batch at a time, conditioning each expansion on confidence and uncertainty signals from completed nodes. A hierarchical context layer propagates compact QueryDocs by default while preserving full execution traces for on-demand recall. The recorded DAG
topology admits structural RL signals that outcome-only recipes cannot define; DAGRPO, a GRPO adaptation, injects
topology-conditioned credit on Executor rollouts and a structural compliance regularization on Orchestrator plans. Across BrowseComp-Plus,
GAIA, and xbench-DeepSearch, DAGent surpasses the strongest open-source baseline by 5.3 / 5.8 / 2.0 points at the Qwen3-235B-A22B scale, and the lead replicates across four open-source backbones and extends to GPT-5 at 327K context. At the Qwen3-8B scale, DAGRPO improves over a same-budget outcome-only GRPO baseline by 3.0 average Pass@1 points. A same-architecture comparison shows that evidence-conditioned planning reaches higher accuracy at lower per-task
token, tool-call, and step footprints than its Plan-then-Patch counterpart. Code: https://github.com/hanwenliu6825/DAGent
Read the full abstract ▾
Robotics
Concurrent Semantic Search and Mission Execution for LTL Missions in Unknown Environments
Fernando Salanova Gaspar, David Morilla Cabello, Cristian Mahulea Poleuca et al. (+1 more)
Planning complex missions in unknown environments requires
robots to reason simultaneously about what they should do and what they still need to discover. Existing approaches for solving LTLf missions typically assume a known environment, or separate the exploration of the environment from the execution of the mission, while semantic exploration methods look for one target at a time and ignore the mission being executed. To fill this gap, our main contribution is an adaptive high-level planning method that interleaves a task-driven semantic search with the execution of the mission, advancing both in a non-myopic manner. Our method leverages two representations built online, a metric-semantic scene graph, built with a
Vision Language Model (VLM), that provides the evidence needed to locate the objects the mission refers to, and the deterministic finite automaton (DFA) encoding the mission, that indicates which of them matter at each mission state. At every planning stage, our planner selects the waypoints that are most valuable for both the semantic search and the advancement of the mission, valuing them over the remaining mission stages in order to avoid blocking states. The selected waypoints are then ordered in a single high-level plan, which is recomputed as new information arrives. In photorealistic indoor environments over five mission types, our method completes more missions than the compared approaches while having to cover less of the environment, and it does so with shorter paths and complying with the restrictions imposed by the mission.
Read the full abstract ▾
All authors Fernando Salanova Gaspar, David Morilla Cabello, Cristian Mahulea Poleuca, Eduardo Montijano Muñoz
Robotics
Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey
F. Olivia Fan and Oliver Obst
Does
memory-dependent control need nonlinear recurrent dynamics? We study simulated air-hockey defence under temporary loss of puck tracking. A DreamerV3 teacher outperforms a memoryless policy under tracking loss, while resetting the teacher's recurrent state sharply reduces performance, which demonstrates that the task requires
memory. We distil this teacher into compact recurrent policies with a 64 dimensional state, with a combination of a diagonal linear recurrence and an optional rank-$k$ nonlinear innovation while retaining nonlinear observation encoders and action heads. Across five matched seeds, the purely linear recurrent model ($k=0$) matches both the GRU baseline and the teacher throughout the tested range of tracking loss. Increasing nonlinear innovation rank providing no measured benefits. This result is obtained on a fresh test split, which will be only opened after all models and analyses are frozen. The linear model requires fewer recurrent parameters and less computation than GRU, but performs comparably. These results suggest that, for this
memory dependent control task, nonlinear representation learning around a simple linear
memory mechanism can be sufficient, and that nonlinear recurrent dynamics are not necessarily required. These conclusions are limited to the simulated task, teacher, state dimension, and blackout horizon considered here, and to policies whose observation encoder and action head remain nonlinear.
Read the full abstract ▾
Computer Vision
OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual Reasoning
Xingming Shui, Dapeng Chen, Bowei Liu et al. (+5 more)
Omni-modal large
language models deployed in real-world environments encounter external noise that can interfere with their perception and understanding of
multimodal inputs. We study their robustness in audio-visual understanding, focusing on question answering under environmental noise and competing
speech. The challenge is to resist acoustic interference while preserving useful audio evidence. On-policy
distillation provides dense teacher feedback on student-generated responses, but uniform
token weighting does not explicitly prioritize positions affected by acoustic interference. We introduce OP-CAD (On-Policy Clean-Audio
Distillation), a curriculum-based privileged self-
distillation framework for robust audio-visual understanding. Training progresses from mild to severe environmental noise and competing
speech, with selective
token-level supervision at each stage. The student generates responses from corrupted audio-visual input, while a frozen teacher uses clean audio and the verified answer to supervise the same response prefixes. To allocate this supervision, OP-CAD compares teacher predictions under clean, corrupted, and visual-only contexts without revealing the answer. These matched comparisons measure sensitivity to audio removal and corruption; a bounded weighting rule emphasizes positions identified by either signal while retaining supervision throughout the response. OP-CAD outperforms the compared methods across all evaluated noise conditions. Paired analyses further show improved preservation of clean-correct answers under strong interference, with no observed aggregate clean-accuracy penalty. These results demonstrate the value of directing clean-teacher supervision toward acoustically sensitive predictions for robust audio-visual
reasoning.
Read the full abstract ▾
All authors Xingming Shui, Dapeng Chen, Bowei Liu, Jingqi Tian, Minfu Li, Kun Yi, Jiapeng Hong, Yansong Tang
Artificial Intelligence
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Kaixing Zhang, Changming Li, Yingdong Shi et al. (+5 more)
Textual skills enable large
language model (LLM) based
agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill
evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution trajectories and sparse task outcomes. This text-only paradigm leaves the
agent's internal representations, which contain rich records of its evolving execution state, outside the skill optimization loop. We ask whether an
agent can improve its external textual skills by reflecting on its own internal representations. We introduce Rep2Skill, a representation-guided framework for self-
evolution on
agent skills. Specifically, upon the collected
agent rollouts, Rep2Skill models their internal model representation trajectories to localize turns that deviate from successful execution dynamics, and it further interprets these signals alongside the execution contexts as actionable textual feedback for targeted skill revision. Experiments on two
agent environments with two open-source LLMs show that Rep2Skill consistently outperforms text-only approaches in the self-
evolution setting, where the same LLM serves as both executor and optimizer without a stronger external model. This establishes a promising direction moving
agent self-improvement beyond text-only reflection.
Read the full abstract ▾
All authors Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren
Artificial Intelligence
Do Self-Evolving Skills Generalize to Held-Out Tasks?
Xihao Piao, Zifeng Wang and Zhen Chen
AI
agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, that can be retrieved and reused when solving new tasks. Self-evolving skill methods keep rewriting these skills after each round of practice on training tasks, and the skill is then used on new tasks of the same kind. We ask a question: does the improvement a skill shows on its training tasks carry over to new test tasks? We test five self-evolving methods and a one-shot skill on six
benchmarks, with the same model, the same
agent, and the same train/test split for every method. Of the 21 skills that improve on their training tasks, 5 keep all of that improvement on the test tasks, 13 keep part of it, and 3 keep none of it. No existing method is best everywhere. When we read the skills, the ones that carry over badly often fix details that should depend on the task, such as column names and output files, or turn a fix for one failure into a rule for every task. An LLM judge that reads the skill content can often see this: it ranks finished skills the same way the test results do in 86% of pairs. But it predicts the effect of a single edit poorly, so edits still have to be tested by running them. Based on these findings, we describe Generalizable Skill Optimization (GSO), which keeps only a guide for writing skills and writes a new skill for each task; it scores highest on all six
benchmarks.
Read the full abstract ▾
Computer Vision
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation
Ruiqi Li, Xuanyi Liu, Sijia Li et al. (+9 more)
Current image-to-
video models achieve visual realism and physical plausibility, but
reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring inference beyond explicit instructions. We introduce MindWorldBench to evaluate mental-state-conditioned
video generation. We formalize this as mental-state-to-behavior
reasoning, where models generate actions from a world state and latent variables without explicit action
prompts. MindWorldBench utilizes Zero-Action Prompting and a counterfactual design with 744
prompts to isolate the causal effects of mental states. An automated pipeline evaluates
video quality, commonsense plausibility, and mental-state consistency. Evaluations of 11 models show that despite visual fidelity and physical
reasoning, models fail to align behaviors with latent mental states. We identify a failure mode, termed Omniscient Bias, where models default to the objective world state rather than human's subjective belief. These results demonstrate a disconnect between visual generation and cognitive
reasoning, suggesting a need for explicit mental-state modeling in
video generation systems. Project website: https://richard2049-lee.github.io/MindWorldBench/
Read the full abstract ▾
All authors Ruiqi Li, Xuanyi Liu, Sijia Li, Haofeng Wang, Yuxin Liu, Feng Xie, Songchao Tan, Shiqi Wang, Hanwei Zhu, Yizong Wang, Chuanmin Jia, Siwei Ma
Artificial Intelligence
MADBench: Benchmarking the Security of Multi-Agent Debate
Yuwan Liu, Jiaming Zhang, Yue Huang et al. (+1 more)
Multi-
agent debate (MAD) can improve large
language model (LLM)
reasoning by allowing multiple
agents to exchange and critique their answers to the same task. However, the interactions that enable
agents to correct mistakes can also spread
adversarial errors and steer the
agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic evaluation of MAD under diverse attacks remains limited. A central question is whether debate mitigates
adversarial influence or amplifies it. In this paper, we present MADBench, a
benchmark for evaluating the security of MAD. We organize attacks into a layered taxonomy following the MAD workflow, incorporating both established attacks and new strategies tailored to debate. We evaluate six attack families over 356 source tasks and 3,958 test cases, examining their effects on the final answer and the propagation of
adversarial influence. Our results show that, under attacks, MAD does not necessarily improve LLM
reasoning. Compared with a single-
agent baseline, MAD can mitigate attacks on answer accuracy in question-answering tasks while amplifying unauthorized reads or writes in both question-answering and workspace tasks. Moreover, even when three out of five
agents collude, the attack changes the final answer from correct to wrong on only 28.30% of tasks answered correctly without attack, while only 3.26% of initially correct honest
agents switch to wrong answers during debate.
Read the full abstract ▾
All authors Yuwan Liu, Jiaming Zhang, Yue Huang, Sisi Duan
Robotics
Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults
Heejae Suh, Jongwook Han, Zahra Gholami et al. (+1 more)
Unreliable visual inputs can harm task performance and cause potential physical safety risks for
vision-
language-action (VLA) models. We analyze how $\pi 0.5$ and GR00T models act under input faults such as image blackouts and freezing. We find that blackout and freezing produce distinct physical failure modes even when task-success rates are similarly low: freezing causes more extreme joint behavior, whereas blackout after gripper closure can cause more object drops, most markedly without proprioception. Selective intervention studies reveal that proprioception (current
robot state) partly compensates for the removed
robot depictions and reduces non-target contact. However, it cannot sufficiently restore task success when wrist-view object information is removed, even when aided by the remaining scene view. We then evaluate two mitigation approaches: camera-blackout training and training-free replacement of faulty visual
embeddings. Both improve task success in selected conditions, but can increase unintended contact or disturbance to surrounding objects. Real-
robot trials further show that successful execution under camera faults can still involve unintended physical interactions. These findings motivate designing VLA policies that use the
robot and object information still available under camera faults to limit hazardous motion.
Read the full abstract ▾
All authors Heejae Suh, Jongwook Han, Zahra Gholami, Yohan Jo
Machine Learning
Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD
Junghoon Seo
We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded additive noise generated by an exogenous uniformly ergodic Markov chain. For a smooth, strongly convex objective with a Lipschitz Hessian and nondegenerate long-run noise covariance, the centered iterate normalized by the square root of the stepsize is $O(\sqrt{\alpha})$-close in 1-Wasserstein distance to its limiting Gaussian. The proof combines blockwise Gaussian comparison with long-run contraction. A four-state example gives a matching lower bound although the one-time noise marginal is symmetric and every nonzero-lag autocovariance vanishes. In this example, an adjacent third-order mixed moment produces the leading correction.
Read the full abstract ▾
Artificial Intelligence
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong et al. (+3 more)
Long-horizon
agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving
agents therefore need
memory extraction methods that improve with more test-time compute without relying on gold labels. We propose RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality
memories without gold labels. Evaluated on AppWorld and BFCL-V3 across multiple context-evolving
agent frameworks, RefCon delivers strong and consistent gains, including relative improvements of 21.6% on ACE and 16.6% on ReMe over no-scaling baselines, while a diversity-focused variant (DivCon) achieves a 35.5% gain on ReasoningBank. RefCon consistently outperforms existing baselines without ground-truth labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines. We further analyze the accuracy-
token trade-off and scaling behavior, showing RefCon maintains favorable efficiency and continues to improve as more trajectories are used, unlike diversity-only scaling which saturates earlier.
Read the full abstract ▾
All authors Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong, Yu-Xuan Huang, Yangkai Ding, Tao Yu
Computer Vision
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning
Yunbei Zhang, Janet Wang, Jihun Hamm et al. (+1 more)
Can structured text replace
vision for diagram
reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanations. Using the same solver model and generation settings, we compare three input conditions: the original image, question-blind structure extracted by a
vision-
language model, or gold structure derived from the diagram source. Validity-triggered recovery tests truncation and schema failure, question-relevant fidelity measures preservation of answer-critical structure, and matched edge interventions test the effect of error location. On a reserved holdout of 240 public FlowGen diagrams, evaluated under a frozen protocol, gold structure reaches 87% accuracy while direct
vision and learned text both remain below 30%. The aggregate comparison includes source-derived relation labels that may not be printed in the image and uses different learned and gold graph encodings, so it does not isolate extraction error alone. Retrying only invalid extractions makes nearly every public representation schema-valid yet leaves accuracy essentially unchanged. The public learned-text deficit relative to gold more than doubles with structural difficulty. Question-relevant
topology predicts correctness better than whole-graph
topology. In an exposed intervention study, a single answer-relevant edge edit reduces the primary solver's original-answer accuracy to near zero, while matched irrelevant edits largely preserve it. Supplied structure requires fewer solving
tokens than
vision, but learned acquisition removes this advantage at single use. These comparisons motivate evaluating acquired text by the answer-relevant evidence it preserves and by the solver's ability to use that representation.
Read the full abstract ▾
All authors Yunbei Zhang, Janet Wang, Jihun Hamm, Chandan K Reddy
Artificial Intelligence
Schema: Discovering Unknown Environments via Agentic Program Induction
Guanning Zeng, Jiani Wang, Wenjie Ma et al. (+8 more)
Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM
agents. Current LLM
agents often record their discoveries in prose, which may not provide a compact, explicit account of how the environment works. Inspired by how scientists organize observations into testable, predictive theories, we introduce Schema, an
agent harness that organizes learning and action through interactive program induction. The LLM
agent decides what to investigate and how to act, expressing its evolving understanding of the environment as executable programs. The harness consists of a persistent program workspace and a small set of interfaces for checking these programs against the interaction history, planning within them, and executing plans under step-by-step verification. Schema raises ARC-AGI-3 RHAE from 58.7% to 99.2% with the same base model, solves 100% of the public DiG-bench games, and reaches the median performance of the top-50 human players on MazeBench. Extensive analysis shows the effectiveness of Schema in unknown mechanism discovery, and ablations confirm the contribution of each component.
Read the full abstract ▾
All authors Guanning Zeng, Jiani Wang, Wenjie Ma, Shaofeng Yin, Chenyang Wang, Shichen Liu, Angjoo Kanazawa, Wode Ni, Xiuyu Li, Andrea Zanette, Haiwen Feng
Artificial Intelligence
BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence
Hongji Pu
Adaptive RAG uses signals such as confidence, relevance, support, and
retrieval quality to decide when to search or correct evidence. In multi-step
retrieval, however, these local signals must be combined into a persistent view of what the current evidence supports, what remains missing, and which action should follow. Existing methods often use such signals as separate triggers, making it difficult to preserve a coherent evidence state across a trajectory; we call this problem evidence-state fragmentation. We introduce BELIEFRAG, a closed-loop controller that updates an explicit state over sufficiency, reliability, conflict, uncertainty, evidence gaps, and acquisition cost, then chooses among
retrieval, query rewriting, verification, answering, stopping, and abstention. Across six QA
benchmarks with gpt-oss-120b, BELIEFRAG reaches mean
token F1 0.572 with 3.89k
tokens per question, outperforming fixed iterative
retrieval (0.555 F1) while using 39% fewer
tokens. The same quality-cost pattern transfers to Qwen3-32B, where BELIEFRAG reaches 0.552 F1 versus 0.523 for iterative
retrieval while using 35% fewer
tokens. Analysis shows that the main gains come from corrective re-
retrieval rather than
pruning alone, while several belief dimensions are redundant and calibrated answerability plays the strongest operational role. Calibration improves threshold stability across related evidence sources, although source shift can still invalidate the same decision signal.
Read the full abstract ▾
Networking
MoSE: Mode-Switching Expander for Mixed LLM Training and Inference
Fan Yang, Ying Zhou, Binglei Wang et al. (+2 more)
AI clusters increasingly run large
language model (LLM) inference and training on the same fabric. Prefill-decode (P-D) disaggregation creates key-value (KV) cache transfers between prefill and decode groups, whereas training collectives and all-to-all traffic benefit from near-uniform global connectivity. A static sparse
topology can therefore be poorly matched to one of the two traffic patterns. We present Mode-Switching Expander (MoSE), a reconfigurable expander that treats
topology design as a fixed-degree edge-allocation problem. MoSE reallocates the same sparse edge budget toward direct P-D connectivity in inference-heavy modes and restores a uniform random regular expander in training-heavy modes. We evaluate MoSE using a 1024-group flow-level
topology model, shortest-path routing, and two mixed workloads. Across 20 seeds, MoSE reduces average and 95th-percentile (P95) load-aware KV communication cost by 90.8% and 91.9% relative to Static-Training in the inference-heavy mode. In the training-heavy mode, it reduces average and P95 training communication cost by 22.7% and 27.6% relative to stale Static-Inference. These results show that coarse-grained
topology switching can support both workload modes without additional ports or routing changes.
Read the full abstract ▾
All authors Fan Yang, Ying Zhou, Binglei Wang, Zhenjie Zhou, Jialong Li
Machine Learning
ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control
Peng Jin, Zihan Qiu, Zekun Wang et al. (+8 more)
Scaling Large
Language Models (LLMs) via Mixture-of-Experts (MoE) enables massive parameter growth with nearly constant per-
token computation. However, further scaling the parameter count requires increasingly sparse routing, where expert load imbalance becomes more severe. This imbalance reduces parameter utilization and training efficiency, and can undermine training stability, becoming a bottleneck to reliable scaling. In this work, we unify two representative auxiliary-loss-free methods as incomplete Proportional-Integral-Derivative (PID) controllers: DeepSeek's loss-free method acts as a fixed-step integral controller, while Kimi K3's
Quantile Balancing functions as a generalized proportional controller. Building on this control perspective, we propose ID Balancing, an Integral-Derivative controller. It scales its integral term with load error and activates its derivative term only when imbalance worsens, enabling stronger corrections for large or worsening errors and smaller updates near balance. Evaluated across Top-$10$, Top-$5$, and Top-$3$ routing over $768$ experts, ID Balancing reduces worst-case backbone MaxVio and training-average backbone MinVio by over $50$% and $12$%, respectively, relative to the best baselines in the Top-$3$ setting. When the total parameter count increases from $18.9$B to $69.9$B (Top-$10$-of-$768$), ID Balancing's worst-case backbone MaxVio remains nearly unchanged and is approximately $89.6$% lower than that of the auxiliary-loss baseline. ID Balancing also maintains competitive
language-modeling and downstream performance. The advantages of ID Balancing grow as sparsity increases, making it a promising solution for scaling larger, sparser MoE models.
Read the full abstract ▾
All authors Peng Jin, Zihan Qiu, Zekun Wang, Bo Zheng, Yang Xu, Tian Xie, Xiao Li, Huaqing Zhang, Haoran Lian, Rui Men, Dayiheng Liu
Computer Vision
Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing
Shenxiang Zeng, Chen Yang, Peiyao Chen et al. (+3 more)
Physical
reasoning from
video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreliable on complex physical tasks without explicit modeling and validation, while predefined tool pipelines rely on task- and domain-specific priors that limit generalization across materials, dynamics, and
reasoning tasks. We introduce Asking the World (ATW), a generalist
agent that constructs and interrogates task-relevant executable worlds through two adaptive stages: World Modeling calibrates a world from
video, while World Probing queries, simulates, and intervenes on it to obtain question-relevant evidence. Rather than prescribing the operations in either stage, ATW determines how to model and probe according to the scene and question. We develop PolyWorld Engine, a lightweight and highly programmable Warp-based multiphysics simulator for constructing and probing worlds with rigid bodies, soft bodies, cloth, ropes, fluids, and their coupled interactions. CEM-based system identification recovers task-relevant dynamics during World Modeling. The resulting world becomes an active workspace for question-directed physical experiments rather than a predetermined downstream tool. We evaluate ATW on CLEVRER, ContPhy, and three real-world scenarios. Using Gemini-3-Flash as its base VLM, ATW achieves 80.82% overall per-question accuracy on CLEVRER, improving direct Gemini-3-Flash by 46.50 points, GPT-5.5 by 13.58 points, and PhysMind by 8.27 points. On ContPhy, it reaches 70.56% overall accuracy, surpassing Gemini-3-Flash by 28.10 points and GPT-5.5 by 3.53 points. Across the three real-world scenarios, ATW achieves 71.67% accuracy, 28.33 points above GPT-5.5. These results establish agentic world modeling and probing as an effective, execution-grounded approach to generalist physical
reasoning. Project page: https://asking-the-world.github.io/
Read the full abstract ▾
All authors Shenxiang Zeng, Chen Yang, Peiyao Chen, Guohui Zhang, Jiansheng Fan, Chen Wang
Computer Vision
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
Shilinlu Yan, Bowen Chen, Yuechen Zhang et al. (+3 more)
Visual-
token compression improves the efficiency of large
vision-
language models, but can expose failures that full-
token evaluation misses. We study
adversarial images that preserve full-
token correctness yet induce errors after compression, even when both inference paths succeed on the clean image. Creating such failures is challenging because perturbing
token importance can also damage the visual content needed for full-
token inference. We propose Feature-Aware
Token Attack (FATA), which couples
attention suppression with cosine-based feature preservation on a fixed set of salient clean-image
tokens. In the primary LLaVA-1.5-7B setting, FATA uses only
vision-encoder gradients, without access to the deployed compressor,
token budget, or downstream task. Across four visually dependent task subsets and four compressors under a controlled reconstruction protocol, FATA achieves SR = 96.3% full-
token accuracy retention and CBR = 22.1% conditional blinding, compared with 89.8% and 15.7% for CAA. Ablations support the role of both objectives in balancing compressed-path failure against full-
token preservation. FATA also has the lowest measured detection rate among four attacks across three evaluated detectors at a 5% false-positive rate. These findings motivate assessing
adversarial robustness jointly across full-
token and compressed inference.
Read the full abstract ▾
All authors Shilinlu Yan, Bowen Chen, Yuechen Zhang, Zhenhong Zhou, Li Sun, Sen Su
Computer Vision
Uncertainty-Aware Consistency Distillation for Few-Step Video Generation
Lingyu Liu, Yaxiong Wang, Li Zhu et al. (+1 more)
We study few-step
video generation, i.e., distilling a multi-step
video generator, which typically requires tens of sampling steps, incurring substantial latency and compute, into a few-step student. Consistency
distillation is a common recipe, in which a multi-step teacher provides the consistency targets for a few-step student. However, these teacher-guided targets are not equally trustworthy, and the content is harder to learn where it varies rapidly over time, e.g., moving foliage shadows or flowing water. We observe that supervision reliability follows the local difficulty of the content rather than semantic complexity: regions that change little yield consistent endpoint predictions, whereas regions with large temporal variation produce larger discrepancies that coincide with the largest perceptual errors. Motivated by this observation, we propose Uncertainty-Aware Consistency
Distillation (UACD), which reweights consistency supervision at each spatiotemporal region using a local, parameter-free uncertainty estimate. Specifically, we construct two independently perturbed teacher-guided consistency paths, whose student endpoint predictions provide a consensus target; the discrepancy between the student's direct prediction and this target is the uncertainty proxy. We then relax the consistency penalty on high-uncertainty regions through an exponential weight, while keeping the full penalty elsewhere, since the student cannot be expected to match targets that are hard to learn. To preserve perceptual quality under aggressive step reduction, we integrate feature-space
adversarial training with semantic
alignment. With parameter-efficient LoRA adaptation of the 50-step Wan model, our method achieves state-of-the-art 4-step generation on VBench 2.0 (0.556 mean score) and is preferred over competing methods in a user study.
Read the full abstract ▾
All authors Lingyu Liu, Yaxiong Wang, Li Zhu, Zhedong Zheng
Machine Learning
Characterizing High Bandwidth Flash for LLM Serving
Zack Yu, Chloe Wong, Coleman Hooper et al. (+7 more)
Large
language model (LLM) serving requires substantial
memory to store model weights and KV caches. As models grow larger and contexts become longer,
memory capacity and bandwidth increasingly become bottlenecks for serving performance. Agentic workloads compound this pressure through repeated interactions over growing contexts, making it increasingly important to retain KV state for reuse. High-bandwidth flash (HBF) offers a way to expand accelerator
memory capacity for large
language model (LLM) serving, but its access costs and limited write endurance complicate its use. We evaluate HBF for high-throughput agentic serving across system design and scheduling choices to understand when additional capacity improves serving performance and energy efficiency. We introduce an HBM-HBF-host hierarchical storage system and buffered cache-aware scheduling, and use trace-driven simulations to analyze their effects on performance, energy consumption, and HBF write lifetime. Across the evaluated workloads, the fastest HBF-augmented systems reduce completion time by 36.1-87.7% relative to HBM-only systems. Modeled energy savings reach 59.1%, with benefits depending on the workload and weight placement. Buffered cache-aware scheduling extends estimated HBF write lifetime from 1.21 to 14.82 years in the evaluated configuration. These results demonstrate the importance of coordinating data placement and scheduling to improve serving efficiency while sustaining a practical HBF write lifetime.
Read the full abstract ▾
All authors Zack Yu, Chloe Wong, Coleman Hooper, Minjae Lee, Wonjun Kang, Youngjin Cho, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
Computer Vision
Perceptual Color Difference Modeling Using Machine Learning and Human Similarity Judgments
Elnara Kadyrgali, Muragul Muratbekova, Adilet Yerkin et al. (+6 more)
Accurate assessment of color differences is essential for applications ranging from digital design to quality control. While existing color difference metrics, such as CIEDE2000, aim to approximate human perception, they may still exhibit inconsistencies with perceptual judgments. In this study, we investigate a data-driven approach to color-difference estimation based directly on human evaluations. We collect similarity judgments for 2,000 systematically generated color pairs, each rated by seven observers using a four-point ordinal scale. These judgments are then used to train regression models using different color representations, including RGB channel differences, HSI differences, and COLIBRI fuzzy linguistic categories. Experiments with five regression
algorithms show that the choice of color model has a greater influence on prediction performance than the choice of regression
algorithm. Using COLIBRI features alone, linear regression achieves an R2 of 0.595, outperforming RGB and HSI representations, which achieve R2 values of 0.479 and 0.493, respectively. The best performance is obtained by LightGBM using the combined representation, reaching an R2 of 0.703. The results indicate that human perceptual color differences are better captured when numerical color coordinates are complemented by graded perceptual categories, highlighting the potential of data-driven models for perceptually aligned color-difference estimation.
Read the full abstract ▾
All authors Elnara Kadyrgali, Muragul Muratbekova, Adilet Yerkin, Nuray Toganas, Ayan Igali, Malika Ziyada, Aruzhan Burambekova, Jamaladdin Hasanov, Pakizar Shamoi
Robotics
Drape-Compatible Tool-Tip Localization for Hand-Held Laparoscopic Instruments via UWB Carrier-Phase Ranging and Trocar-Constrained Geometry
Jinseok Lee, Dongho Yee, Minsung Kim et al. (+8 more)
A
surgical robot policy needs to know where each instrument's working end sits relative to the camera and to the other instrument, yet a laparoscopic operation leaves only the endoscope
video, and a draped instrument hides every optical path on itself. We estimate the tool tips from distances and an IMU alone. The distances are measured by ultra-wideband carrier phase between
antenna nodes on the handle side of the instruments: one per hand-held instrument, one on the endoscope, all outside the sterile barrier. Take the endoscope
antenna as the reference. The two instrument
antennas carry six coordinates while the three pairs give three distances, so the problem is short by three, and averaging cannot close that gap because what is missing is information, not precision. Carrier phase adds one more unknown per pair, an integer that leaves distance fixed only modulo lambda/2 = 23.1 mm. The trocar settles both difficulties: each shaft passes through a port whose position is known and whose direction the on-board IMU measures, so its
antenna keeps a single degree of freedom, the insertion depth. Two unknowns now face three distances – two fix the depths and the third is left over, and that spare equation exposes a wrong integer or a wrong mounting offset instead of absorbing it. The same solve returns both tool tips in the endoscope frame, without the second carrier frequency that integer resolution usually needs, so the link never leaves a single PLL lock. In an 11-hole phantom among metal instruments the three distances hold sigma = 0.10-0.33 mm at 35-46 Hz, a sterile drape pressed onto the
antennas leaves the link unchanged where an optical path would be blocked, and the logger was carried into a live rabbit appendectomy.
Read the full abstract ▾
All authors Jinseok Lee, Dongho Yee, Minsung Kim, Younghoon Noh, Seonho Shim, Juahn Oh, Yechan Seo, Jiyul Lee, Seong Jeong, Hyuk Choi, Hyoun-Joong Kong
Computer Vision
GeoGAT: Bidirectional Temporal Sampling Meets Hierarchical Graph Attention for Global Video Geo-localization
Junchao Cui, Xuanzi Ma, Wenqi Shi et al. (+4 more)
Global
video geo-localization aims to infer the geographic location of a
video worldwide, evaluating performance across four geographic hierarchies: city, state/province, country, and continent. Existing methods typically employ one-way uniform sampling to process
video frames and train independent classifiers for each hierarchy, which leads to the loss of key geographic cues and prediction conflicts between hierarchies, especially for complex multi-shot edited
videos. To address these limitations, we propose GeoGAT, which integrates bidirectional temporal sampling with graph
attention networks (GATs). Specifically, GeoGAT extracts forward and offset-reversed frame sequences to construct complementary spatiotemporal features. These fused features are then fed into a predefined geographical hierarchy graph, where GATs perform structure-aware message passing, while a dual-constraint mechanism prunes predictions to eliminate cross-hierarchy conflicts. We construct GeoGAT10k, comprising 9,720 multi-shot edited
videos from 166 cities worldwide, specifically to
benchmark generalization ability on complex
video structures. Experimental results on CityGuessr68k and GeoGAT10k demonstrate that GeoGAT eliminates hierarchical conflicts entirely and achieves state-of-the-art performance across all four geographic hierarchies. On CityGuessr68k, GeoGAT outperforms the strongest baseline, evaluated under both classification and
retrieval protocols, by 2.6 percentage points at the city level. On the more challenging GeoGAT10k with multi-shot edited
videos, the accuracy improvement exceeds 24 percentage points, validating strong generalization to complex real-world scenarios.
Read the full abstract ▾
All authors Junchao Cui, Xuanzi Ma, Wenqi Shi, Hangyu Li, Biru Zhu, Chong Fu, Xiangyang Luo