Numerical Analysis
High Performance Computing of SDRE models with Discrete Kalman Filtering for Robust $H_{\infty}$-Controls
Yunfeng Cai, Tiexiang Li, Wen-Wei Lin et al. (+1 more)
State-dependent Riccati equation (SDRE) control requires repeated online solution of continuous-time algebraic Riccati equations (CAREs). A projected-channel $H_\infty$ formulation preserves the physical actuator and sensor dimensions of under-actuated, partially observed systems. We derive a computable sufficient attenuation bound for positive-semidefinite stabilizing Riccati solutions and construct an update that enforces their spectral-radius coupling condition. A discrete Kalman recursion supplies the scheduling state estimates. The two CAREs arising in controller synthesis are solved by a structure-preserving doubling
algorithm (SDA) or a warm-started Newton–Kleinman iteration equipped with a doubling Lyapunov solver. Numerical studies use a twelve-state F-16 model with complete aerodynamic forces, moments, and trim, together with quadrotor spiral tracking. With instantaneous command updates, all three CARE backends give essentially the same closed-loop response. In the tracking simulations, measured computation times determine when new control inputs are applied, and the previous inputs are held during computation. SDA and Newton reduce airspeed and pitch errors in all six paired aircraft tracking runs. In the faster quadrotor task with limited computational resources, SDA and Newton complete all paired runs, while runs using MATLAB icare terminate early.
Read the full abstract ▾
All authors Yunfeng Cai, Tiexiang Li, Wen-Wei Lin, Junxin Zhang
Computer Vision
On-Policy Visual Evidence Distillation
Shaohang Wei, Feifan Song, Guangyue Peng et al. (+9 more)
Visual
agents solve problems by interleaving
reasoning with image operations, and on-policy
distillation (OPD) provides guidance from a strong teacher on student-generated interaction trajectories. However, image operations change the evidence available for subsequent
reasoning, so local errors in evidence acquisition (Acquire), reading (Read), or answer grounding (Ground) can propagate through the trajectory and lead to incorrect answers. Existing
multimodal OPD methods primarily construct or contrast auxiliary views of the original image to strengthen supervision, without explicitly modeling the connections between student actions, resulting observations, and subsequent
reasoning. This limits their ability to provide corrections tailored to different failure stages. We introduce Reflection on Visual Evidence (ReVuE), an on-policy
distillation method for visual
agents. ReVuE compares multiple student-generated trajectories for the same query, summarizes the observed visual evidence, and diagnoses the first failure across the Acquire, Read, and Ground stages. The resulting reflections provide training-time context for the teacher. We group and reweight
token-level
distillation losses according to how strongly these reflections affect the teacher's predictions. This design translates trajectory-level evidence diagnosis into targeted
token-level supervision, guiding students to improve their visual evidence acquisition and
reasoning. Across 11
benchmarks spanning the Qwen2.5-VL and InternVL3.5 model families, ReVuE outperforms all evaluated OPD baselines in weighted-average scores for perception, mathematical
reasoning, and general tasks. ReVuE also reduces redundancy in
reasoning and tool calls while improving tool-call accuracy and task accuracy. Code is available at https://github.com/sylvain-wei/ReVuE
Read the full abstract ▾
All authors Shaohang Wei, Feifan Song, Guangyue Peng, Wenhao Yu, Wei Li, Wen Luo, Yang Xu, Yufan Shen, Luke Mao, Yang Du, Asher Qin, Houfeng Wang
Computer Vision
You Cannot Recover What Was Never Measured: Quantifying the Information Ceiling of Ultra-Low-Field MRI Super-Resolution
Prathamesh Pradeep Khole, Shreya Handa, Utkarsh Gupta et al. (+1 more)
Generative super-resolution models can turn portable 64 mT MRI into images that look like 3T scans, and the field evaluates them with PSNR, SSIM, and pixelwise uncertainty, most often on pairs built by synthetically degrading high-field images. Prior work acknowledges that these models hallucinate and that the problem is ill posed, but to our knowledge no study measures how much information about the individual subject the real low-field scan actually contains. We measure it. Using paired 64 mT and 3T scans of the same subjects from three public
datasets, and a measurement protocol validated on tests whose correct answer is known in advance, we find that, judged over the whole
brain, real 64 mT scans carry structure specific to the individual only down to approximately 3 to 4 mm half-pitch in plane, and coarser still through plane. Standard synthetic degradations preserve subject information roughly 1 mm beyond this ceiling, so models trained and benchmarked on synthetic pairs are evaluated on information that real scanners never record. We then test trained
diffusion models and a publicly released external model on real paired acquisitions; 24 trained runs of five architectures (GAN,
diffusion, and
transformer families) give the coverage of the audit. On every subject where faithfulness can be measured, fine output detail is no more correlated with the subject's own 3T scan than with a stranger's, while sample-variance uncertainty does not distinguish fabricated structure from reconstruction difficulty. Because PSNR and SSIM score resemblance to a reference rather than whether detail belongs to the subject, a
benchmark scored by them cannot tell recovery from fabrication. Code for the measurement protocol will be released so that recoverability claims can be tested for newer models.
Read the full abstract ▾
All authors Prathamesh Pradeep Khole, Shreya Handa, Utkarsh Gupta, Razvan Marinescu
Artificial Intelligence
ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction
Zheyu Shen, Guanhua Wang, Dezhan Tu et al. (+5 more)
Long-context large
language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for long, reusable context prefixes, whose cache must serve many downstream queries. Reconstruction-based methods such as
Attention Matching achieve strong downstream task performance with compact KV caches. However, iterative anchor search dominates the compaction cost of OMP-based
Attention Matching. This motivates our selective amortization principle of learning a reusable anchor-selection policy across contexts while retaining context-specific reconstruction. In this work, we propose ARC-KV, a novel reconstruction-based KV cache compaction method that follows this principle. To this end, we first train a value-aware indexer to select real-key anchors in a single scoring pass. ARC-KV then applies convex-hull-constrained key merging and fits an
attention-mass bias and compact values against the full cache. At inference time, ARC-KV builds the compact cache once per context using the frozen indexer and reuses it for all subsequent queries. Extensive experiments demonstrate that ARC-KV outperforms reported compaction methods in most settings across QuALITY, RULER, and LongBench on Llama-3.1-8B-Instruct. In particular, at 10% KV retention on QuALITY, ARC-KV improves accuracy from 0.6409 to 0.6474 over
Attention Matching while reducing compaction time by a factor of 25.73, from 959.8 s to 37.3 s.
Read the full abstract ▾
All authors Zheyu Shen, Guanhua Wang, Dezhan Tu, Mengchi Zhang, Yanjia Li, Adnan Aziz, Chunqiang Tang, Ang Li
Computer Vision
Motion Concept Unlearning in Video Diffusion Models
Ping Liu and Chi Zhang
Text-to-
video (T2V)
diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that motivate targeted concept erasure. Although concept erasure has been extensively studied for static concepts in text-to-image and T2V models, erasing motion concepts remains largely unexplored. We present a systematic study of motion concept erasure in
video Diffusion Transformers (DiTs). Through causal interventions, we show that text-conditioning
attention carries concept-specific motion information and supports selective intervention, whereas perturbing temporal positional encoding suppresses both target and non-target dynamics. We further find that directly adapting ESD, a representative weight-level image erasure method, to a
video DiT yields modest and uneven motion suppression: reducing its erasure training loss does not by itself remove the concept signal from the difference between the conditional and unconditional predictions, which classifier-free guidance (CFG) then scales at every denoising step. From these findings, we derive three requirements for motion concept erasure: concept specificity, spatial selectivity, and temporal naturalness. Each determines one component of MUTE (Motion concept Unlearning in Text-to-
video gEneration): at each denoising step, MUTE extracts a concept direction through
token neutralization, derives a spatial gate from the direction's intrinsic structure, and subtracts the resulting correction from the velocity output before CFG is applied. MUTE is training-free and requires no weight modification. Experiments on 20 motion concepts show that MUTE outperforms representative
prompt-level, weight-level, and inference-time baselines on Wan2.1-T2V, and the same formulation transfers to CogVideoX, supporting its applicability across distinct T2V
attention architectures.
Read the full abstract ▾
Artificial Intelligence
Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training
Chenliang Li, Neiwen Ling, Zijun Wei et al. (+1 more)
Fully asynchronous reinforcement learning (RL) improves resource utilization in large
language model post-training by overlapping rollout generation with policy optimization, but it also introduces policy lag as trajectories are generated and queued while the trainer continues to update. We study how this lag accumulates over a trajectory's lifetime and how it can be controlled without sacrificing the wall-clock benefits of asynchronous execution. We decompose trajectory staleness into Generation Staleness, accumulated before rollout completion, and Waiting Staleness, accumulated after a completed trajectory enters the pool. Motivated by this decomposition, we introduce PACE (Pool-Aware Control of Effective Staleness). PACE converts excess pool occupancy into an adaptive rejection budget and ranks completed trajectories using an effective-staleness score that combines Waiting Staleness with prefix-aware Generation Staleness. This avoids penalizing long or interrupted rollouts solely because they span multiple policy versions. In single-turn mathematical
reasoning, PACE improves the six-
benchmark average validation accuracy by 18.7% over unfiltered asynchronous RL at the same wall-clock budget and matches synchronous RL performance with 47.1% less GPU time. PACE also improves validation performance in multi-turn tool-integrated
reasoning, outperforming both synchronous and unfiltered asynchronous RL. Further experiments with the mixture-of-experts model and an alternative RL
algorithm support its applicability across model architectures and training
algorithms.
Read the full abstract ▾
All authors Chenliang Li, Neiwen Ling, Zijun Wei, Alfredo Garcia
Artificial Intelligence
The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents
Xueqi Li, Jingjie Ning and Yibo Kong
An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability when a default-aligned whole plan is removed. We call the risk of interpreting the latter as weak responsiveness to alternative priorities the default trap. We compare paired plans that prioritize different information targets with a shared no-plan reference. An accounting identity relates these distinct behavioral contrasts. Across 3,200 decision windows on 160 selected Retail, Airline, and AgentDojo tasks, switching priorities strongly redirects two models' choices, while the two plan-versus-default contrasts differ. In 2,160 additional windows, reversing account-list order shifts default target selection by 63.3-98.3 percentage points; priority-switching effects remain 96.7-100.0 points in either order. A separate 3,240-window component study finds strong control under single priority sentences, with effects of additional text varying by group and direction. Finally, 1,080 full-task episodes yield observed success differences of -19.4 to +8.3 points relative to no plan. All Retail and Airline success intervals include zero; AgentDojo results describe four fixed application worlds. These findings support joint reporting of priority responsiveness, presentation-dependent defaults, and task success and cost.
Read the full abstract ▾
Artificial Intelligence
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Wenxiao Fan, Jingling Fu, Lichen Ma et al. (+6 more)
Post-training quantization (PTQ) lowers deployment cost for
multimodal large
language models, but calibration typically reconstructs fixed sequences with local objectives. This overlooks autoregressive feedback: a quantization-induced
token change redirects the prefix and changes future states. Yet on-policy coverage alone is insufficient because many decision mismatches barely affect future generation. We propose OnPTQ, an on-policy framework that calibrates on trajectories visited by the current quantized policy. On shared prefixes, OnPTQ identifies quantization-eroded boundaries, evaluates competing
tokens through short counterfactual rollouts, and combines current discrepancy with branch consequence into a Decision–Consequence risk. The risk prioritizes critical states, while context anchoring and trajectory refresh preserve
multimodal behavior and keep calibration aligned with the updated policy. We further derive a Decision–Consequence bound linking behavioral deviation to current policy discrepancy and action-conditioned future-value span. Across
vision–
language and omni-modal Qwen models under multiple low-bit settings, OnPTQ improves downstream performance and yields fewer correctness flips against the corresponding Dense/FP16 references, without changing the deployed inference graph.
Read the full abstract ▾
All authors Wenxiao Fan, Jingling Fu, Lichen Ma, Yu He, Luohang Liu, Jinbao Xue, Ke Zhang, Junshi Huang, Kan Li
Computer Vision
Zhenghao Ni, Weimin Qiu and Meng Tang
Video generation models have demonstrated emerging zero-shot capabilities for visual
reasoning, perception, and other
vision tasks. However,
diffusion-based
video generation is inherently
stochastic, while many downstream
vision tasks are deterministic. Motivated by the effectiveness of self-consistency in chain-of-thought
reasoning for large
language models, we investigate whether self-consistency can similarly improve
diffusion-based
video reasoning. We first introduce a training-free test-time scaling method that samples multiple
video generations and aggregates their predictions through self-consistency. Specifically, we aggregate extracted paths, locations, or masks from multiple rollouts into a consensus prediction. To reduce the inference overhead of multi-rollout generation, we read out predictions early in the denoising trajectory, which preserves consensus quality while reducing denoising steps by more than half. We further propose Rejection Fine-Tuning (RFT) to distill consensus predictions into the
video generation model. The resulting model internalizes the benefit of multi-sample consensus and requires only a single generation at inference time, while substantially outperforming the original model. Experiments on three tasks, including maze solving, visual search, and referring
segmentation, show that both our self-consistency inference and consensus
distillation dramatically improve
video-based perception and
reasoning, without requiring ground-truth
videos or task-specific verification. For visual search, self-consistency raises task accuracy from 48.4% for a single generation to 99.0%. The distilled model retains much of the consensus benefit with a single rollout. For 4-by-4 maze solving, consensus-based training improves the single-generation strict success rate from 72.0% to 84.0% with the same inference latency.
Read the full abstract ▾
Social and Information Networks
Luxury resale volume and composition shifted during the COVID-19 tourism shock, but co-purchase network tests were inconclusive and construction-sensitive
Tengfei Shao
Japan's 2020 tourism shock coincided with 27% fewer buyers and 35% lower gross merchandise value at one second-hand luxury resale intermediary. We compared 2019 and 2020 co-purchase projections of recorded brand labels with a Holm-corrected battery of five label-invariant metrics and Portrait Divergence against two permutation nulls rebuilding both graphs. Neither test separated the full years (smallest Holm p 0.407; 0.097 under the design-matched paired-swap null). For one random two-block split of brands, the battery detected a planted redirection of 30% of multi-brand baskets (178 of 10,399 second-group baskets, 1.7%) in 83 of 100 simulations (83-92 of 100 across 11 splits, all at least 80); Portrait Divergence reached 80% power only at full redirection. Observed falls in mean degree and clustering resembled those of 20-30% redirection, but the planted rise in degree assortativity was absent. A composition-only model of the observed attrition would be detected in only 15 of 100 simulations. Results moved with construction: without residual and material labels (post hoc), mean degree separated the years under the paired-swap null (Holm p = 0.030), and Portrait Divergence fell below 0.05, unadjusted, at the widest construction and within April-December. Shock-period network comparisons need rebuilt-graph nulls and a per-metric detection floor.
Read the full abstract ▾
Computer Vision
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection
Wenpeng Mu, Junshan Jin, Tanfeng Sun et al. (+2 more)
The rapid
evolution of image generators calls for forensic cues that generalize beyond known generation mechanisms. Existing detectors often rely on static image representations or endpoint reconstruction discrepancies, leaving the
evolution of intermediate reconstruction stages underexplored. We observe that the relative
token predictability of real and generated images can reverse across reconstruction scales, suggesting that intermediate stages may expose forensic evidence overlooked by endpoint comparisons. Motivated by this observation, we propose RED (Reconstruction
Evolution Dynamics), a framework that captures transferable forensic cues from coarse-to-fine reconstruction
evolution. To our knowledge, RED is the first framework to use scale-wise
token predictability to guide forensic evidence aggregation across intermediate reconstruction states. It represents the reconstruction trajectory produced by a frozen multiscale VQ-VAE in the shared feature space of a frozen CLIP encoder. To connect the observed predictability variations with visual evidence, RED learns image-adaptive stage weights from scale-wise
token negative log-likelihoods provided by a frozen VAR model. A cross-stage evidence aggregation module then jointly models the original-image representation and the weighted reconstruction features, capturing complementary forensic cues through interactions along the reconstruction trajectory. Experiments on six diverse
benchmarks demonstrate that RED achieves the highest average accuracy of 92.5% and average precision of 97.5% among the evaluated methods. Further evaluations show strong robustness to common image degradations, supporting the value of reconstruction
evolution for generalizable AI-generated image detection. The code will be made publicly available upon acceptance of this paper.
Read the full abstract ▾
All authors Wenpeng Mu, Junshan Jin, Tanfeng Sun, Xinghao Jiang, Qiang Xu
Machine Learning
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
Wenbin Hu, Huihao Jing, Haochen Shi et al. (+3 more)
Group Relative Policy Optimization (GRPO) is widely used to train
reasoning language models, where it computes advantages by centering and normalizing rewards across rollouts of the same
prompt. For multiple rewards, GRPO sums the reward components and normalizes the total reward by its within-group standard deviation. The corresponding variance equals the sum of all pairwise reward covariances. For a fixed centered reward, larger aggregate covariance produces smaller advantages, and vice versa, allowing update magnitudes to adapt to reward dependence. However, correlated rewards with large scales can dominate this normalization and suppress signals from smaller-scale rewards. We propose Correlation-Normalized GRPO (CorrGRPO), which normalizes pairwise covariances into Pearson correlation coefficients. CorrGRPO keeps the centered total reward unchanged while balancing the influence of differently scaled rewards on the correlation-based normalization. This allows advantage magnitudes to adapt to reward correlations without the normalization being dominated by large-scale reward components. We compare CorrGRPO with GRPO and other variants on code generation, tool calling, and
agent security, using models ranging from 0.5B to 8B parameters. These tasks all involve multiple rewards that can improve together or present tradeoffs. Results show improvements across three domains, including code generation, tool calling, and
agent security. Our code is available at https://github.com/HKUST-KnowComp/CorrGRPO.
Read the full abstract ▾
All authors Wenbin Hu, Huihao Jing, Haochen Shi, Yuxuan Liu, Haoran Li, Yangqiu Song
Cryptography and Security
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation
Zonghao Ying, Xiangfan Wu, Bo Yang et al. (+5 more)
Indirect
prompt injection embeds malicious instructions within external content retrieved by LLM-based
agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks (13 methods), channels (16 carriers across text and file modes), and defenses (9 prevention strategies and 3 offline detection baselines). Built on a decorator-based registry, pikit enables seamless extension of custom components without modifying core code, while a unified craft() API composes arbitrary attacks and channels in a single call. We evaluated the toolkit on the pi coding
agent powered by an anonymized LLM in a production-like environment. Benchmarking 9 prevention strategies against high-risk attacks yields a 71.8% relative reduction in attack success rate, with few\_shot\_warning and instruction\_hierarchy providing the strongest protection. Offline detection baselines achieve perfect precision but low recall, demonstrating that heuristic detectors complement rather than replace
prompt-level defenses. To ensure reproducibility, each run automatically logs full
prompts,
agent event traces, session transcripts, and verdict records. Our code is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/pikit.
Read the full abstract ▾
All authors Zonghao Ying, Xiangfan Wu, Bo Yang, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo
Machine Learning
Towards Better Training Signal: Advantage Clipped Policy Optimization
Ruichuan Huang, Jinghan Liu and Congliang Chen
Reinforcement learning (RL) has become a cornerstone for improving the
reasoning capabilities of large
language models (LLMs), but the need for on-policy data substantially limits training efficiency. Reusing off-policy data through importance sampling (IS) can improve efficiency but introduce considerable instability. Hence,
algorithms such as PPO and GRPO widely adopt IS-ratio clipping to stabilize training. However, training stability and gradient estimate are mainly determined by the product of IS ratio and advantage. To further stabilize training, we propose ACPO, which clips the product of the IS ratio and the advantage, leading to more stable gradient estimates. We also establish a connection between ACPO and gradient clipping in policy mirror descent (PMD), which is a standard technique to stabilize optimization process, and prove the convergence of clipped-PMD under the standard RL setting. Experiments on widely used mathematical
reasoning benchmarks show that ACPO consistently outperforms PPO and GRPO in both accuracy and training efficiency, delivering 4-6 percentage points gains on standard math
benchmarks, with Qwen3-8B+PPO. Hence, ACPO is a practical and effective alternative to conventional IS-ratio clipping for RL post-training of LLMs.
Read the full abstract ▾
Computer Vision
CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval
Zhen Liu, Letian Li, Jinpeng Wang et al. (+4 more)
Partially Relevant
Video Retrieval (PRVR) seeks to retrieve untrim-med
videos containing a moment that matches a text query, without temporal annotations. The relevant moment may last only seconds within a
video spanning several minutes, creating an extremely low signal-to-noise ratio that makes PRVR more challenging than standard full-
video retrieval. This task presents two intertwined challenges: (1) signal dilution, where coarse global representations blur the brief relevant signal into the dominant irrelevant surroundings;(2)
curvature rigidity, where
embedding all
videos in the same fixed-geometry space distorts representations for
videos that range from flat atomic events to deep compositional hierarchies. Existing PRVR methods have improved moment selection and cross-modal matching, but they still typically encode all
videos in a single fixed-
curvature retrieval space, limiting their ability to model diverse
video structures. To address both challenges, we propose CurvSpec, a framework that learns content-adaptive
curvature for
video retrieval representations rather than imposing a fixed
geometric prior. CurvSpec processes features through parallel Euclidean and
hyperbolic attention layers, with independently learned
curvatures assigned to the
hyperbolic layers, and a content-aware fusion mechanism routes each input to its most suitable
geometric regime. To further suppress signal dilution, CurvSpec represents each
video with semantic centroids whose number is determined by the
video's content complexity, projects them onto the learned
manifold, and matches each query against its nearest centroid by geodesic distance. Experiments on ActivityNet Captions, TVR, and Charades-STA demonstrate state-of-the-art
retrieval performance.
Read the full abstract ▾
All authors Zhen Liu, Letian Li, Jinpeng Wang, Shuzhao Xie, Yuzhi Huang, Jingyan Jiang, Zhi Wang
Machine Learning
RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning
Chuanpu Liu, Miao Yu, Yikai Cai et al. (+5 more)
Large
language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational
circuits. However, existing
circuit studies emphasize preserving functionality or explaining safety, leaving the mechanisms underlying failures across a broader range of tasks largely unexplored. Extending
circuit analysis from abilities to errors, we explore the perspective that such failures may likewise arise from erroneous internal computations and that targeted tuning of the corresponding parameters can correct such errors while largely preserving other capabilities. Motivated by this insight, we introduce RESCUE (
Reasoning-Error Sparse-
Circuit Uncovering and Editing), a framework that localizes error-associated
circuits and surgically repairs them for performance enhancement. General tasks typically involve multi-step
reasoning and long-form generation, where early deviations can cause prefixes to drift from supervised references, leading SFT-based mask optimization to overlook
circuits involved in generation-time errors. RESCUE therefore refines these masks through reinforcement learning with multiple masked-model rollouts, improving their relevance to observed task failures. Finally, RESCUE introduces a
pruning technique and precisely fine-tunes error
circuits to correct task failures, thereby translating error localization into a sparse and targeted model update. We validate RESCUE on heterogeneous repair sets across two domains: (1) mathematical
reasoning, identifying a math error
circuit of 1.40% density whose repair raises accuracy from 6.0% to 75.5%; and (2) medical QA, where a similarly compact 1.44%
circuit improves repair-set accuracy from 0% to 81%. Our code is available at: https://github.com/chuanpupig/RESCUE.
Read the full abstract ▾
All authors Chuanpu Liu, Miao Yu, Yikai Cai, Yuanhe Zhang, Zhenhong Zhou, Li Sun, Zuming Jiang, Yufei Guo
Machine Learning
Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows
Junhyun Ha, Juho Lee and Byoungwoo Park
Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions having high critic values with low behavior density. Directly refining behavior proposals may be an alternative, yet Gaussian or deterministic editors limit expressiveness to represent multiple separated modes for the same proposal. In this work, we introduce Proposal-Conditioned Refinement Flows (PReFlow), a policy extraction method combining critic-based proposal selection with a conditional refinement flow. To optimize proposal selection and refinement together, we formulate a KL-regularized objective whose optimum induces a Gibbs policy over final actions under a Gaussian-smoothed behavior prior. The refinement flow can represent multiple high value modes, while a proposal-centered Gaussian reference regulates large action changes. This Gaussian reference further enables us to make use of simulation-free, closed form adjoint matching targets from sampled endpoints and critic gradients, yielding a single velocity regression loss without a backward adjoint solve. On 50 OGBench tasks, PReFlow achieves competitive offline performance and the highest aggregate score among the compared methods after online fine-tuning, reaching 91% after 500K environment steps.
Read the full abstract ▾
Computer Vision
MeteoVerse: Unified Weather-Controllable Video World Model
Renlong Wu, Guanqiao Wang, Xuan Shang et al. (+5 more)
Video world models aim to predict future content from an observed scene while following prescribed camera motion. Real-world scene
evolution is determined not only by changes in viewpoint and object dynamics, but also by environmental conditions such as weather, which can substantially alter scene appearance and visibility. Modeling such realistic weather
evolution is challenging because the required weather modification depends jointly on the observed and desired weather states. Depending on their relation, the model may need to preserve, introduce, or remove a weather effect. Existing
video world models typically leave this weather transition implicit, forcing the generation backbone to infer weather
evolution together with scene dynamics and camera motion, which leads to imprecise weather control. To address this limitation, we propose MeteoVerse, a unified weather-controllable
video world model that generates future
videos from a single sunny or adverse-weather image, conditioned on a weather-free scene description, a target-weather instruction, and a camera trajectory. Rather than conditioning only on the desired weather, MeteoVerse explicitly estimates the observed and target weather states and represents the required weather transition. A transition-aware mixture of weather experts then translates this transition into category-specific residual weather features, unifying weather preservation, introduction, and removal while enabling fine-grained control over introduced weather intensity. We further construct the MeteoVerse
dataset with over 50K real-world weather
video clips, generated sunny counterparts, disentangled scene and weather descriptions, weather-intensity annotations, and camera trajectories. Extensive experiments demonstrate substantially improved weather controllability while retaining competitive scene consistency and camera-control performance.
Read the full abstract ▾
All authors Renlong Wu, Guanqiao Wang, Xuan Shang, Yin Hanming, Xiaoxiao Sheng, Tianyu Huang, Hui Li, Wangmeng Zuo
Artificial Intelligence
Geometry-Conditioned Fixed-Scaffold Encoders for Time-Warp Robust Sequence Retrieval
Cassandra Yang and Yufan Tang
Embedding-based
retrieval is attractive for long sequence collections because each item can be encoded once and searched by nearest-neighbor ranking. The difficulty is that the objects being indexed are often observed under a noncanonical clock: cardiac cycles stretch with rate,
speech changes with tempo, and sensor traces reach comparable states at different speeds. This paper studies a specific source of instability in patch-based encoders for this regime. If patch boundaries are chosen from signal geometry, then the tokenization can change under the same temporal deformation that the representation is expected to tolerate. We propose GeoPatch, a fixed-scaffold patch encoder that keeps
token support independent of geometry and uses slope,
curvature, acceleration, affine-residual, and confidence descriptors only as continuous conditioning variables. The design turns boundary variation into feature modulation: geometry can change the
embedding through a controlled pathway, but it cannot change the number, order, or support of local
tokens. We formalize this distinction through a mechanism-level stability analysis that separates boundary drift, affine timing variation, confidence-weighted geometry perturbation, and
retrieval-margin effects. The same local
tokens support global
embedding retrieval and late-interaction scoring, so the scoring rule can be matched to the evaluation protocol. Across ECG,
speech, and multivariate time-series
retrieval tasks, GeoPatch improves early-rank
retrieval under timing variation while exposing a clear trade-off between local surface matching and strict non-overlap
retrieval.
Read the full abstract ▾
Robotics
Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
Long Li, Qichao Zhao, Yue Yang et al. (+6 more)
Current
embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the kind of reflection behind the gains of thinking in
language models. We test whether they can repair a known error, which requires producing a correction and judging whether it is right. Stopped at a failure and allowed to retry, they seldom repair it through their own randomness or from a
language description of the error, and best-of-N selection cannot pick the successful candidate after a failure. We attribute this to training only on successful demonstrations and to inputs too narrow to show what went wrong, and conclude that reflection must come from a
vision-
language model (VLM), which takes in far more information, such as the episode history and text, and is more general. Prior VLM-led work has the VLM plan every step and invoke the
embodied model as a tool, placing the VLM on the critical path. We propose Spotter, which reverses the roles: the
embodied model leads and executes continuously, while the VLM runs in parallel, monitors through a lightweight local screener, intervenes only when an error is detected, reflects on and corrects it, and returns control. We run Spotter with Qwen and with GPT as the VLM, and both improve the
embodied models; with GPT, Spotter improves Cosmos Policy and $\pi_{0.5}$ by 5.6 and 7.5 percentage points on RoboCasa, and raises $\pi_{0.5}$ from 47.2% to 57.0% on the Hard setting of RoboTwin 2.0 and from 53% to 83% on a real
robot. Because the VLM steps in only when an error is confirmed, a successful episode with Qwen takes only 13 to 16 s longer than with the
embodied model alone and about 70% less time than with a VLM-led baseline using the same model. Our code is available at https://github.com/zqc3117/Spotter.
Read the full abstract ▾
All authors Long Li, Qichao Zhao, Yue Yang, Fan Xu, Zhe Wang, Alan Wee-Chung Liew, Chao Qu, Heng Tao Shen, Shirui Pan
Software Engineering
XRepoSkill: Learning Transferable Skills for Software Engineering Agents
Yaoqi Guo, Haoyang Zhou, Jiayi Zhang et al. (+7 more)
Software engineering
agents increasingly use reusable skills distilled from prior experience to resolve repository-level issues, yet such skills often fail to transfer across repositories. A central challenge is that a behavior appearing in a successful trajectory is not necessarily responsible for the successful outcome: it may be genuinely useful, merely incidental, or simply a recurring habit of the model. We introduce XRepoSkill, a trajectory-based approach for learning transferable skills. We represent a skill as a collection of rules, each specifying what action to take and when to take it during issue resolution. XRepoSkill first contrasts successful and failed trajectories of the same
agent on the same issue and derives candidate rules from where their execution paths diverge. Each rule is paired with an executable predicate that enables its prescribed behavior to be evaluated systematically on other trajectories. A rule is verified based on its association with successful issue resolution and retained only when its prescribed behavior recurs across multiple repositories; repository-specific variants of the same behavior are then consolidated into transferable rules. For a new issue, XRepoSkill selects relevant rules to guide the
agent. We learn skills from publicly released trajectories on the official SWE-bench Verified leaderboard and evaluate them on SWE-bench Pro and DeepSWE using three backbone LLMs from different vendors; none of the evaluation repositories appears in the skill-learning trajectory pool. Against three recent skill learning methods, XRepoSkill achieves the highest issue resolution rate in all six
benchmark–LLM combinations. In particular, on the challenging long-horizon DeepSWE
benchmark, XRepoSkill improves issue resolution by 10.3 percentage points over the same
agent without learned skills and by 5.0 points over the strongest skill-learning baseline.
Read the full abstract ▾
All authors Yaoqi Guo, Haoyang Zhou, Jiayi Zhang, Yiran Zhang, Yang Liu, Qiuyuan Chen, Qiang Lin, Hande Dong, Jie M. Zhang, Zhenpeng Chen
Artificial Intelligence
CANTO: CAD-Native Transformer Operators for AI-Aided Engineering
Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn et al. (+8 more)
Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Evaluating design changes through numerical simulation requires meshing the continuous geometry, a computationally expensive and often brittle process that can require manual intervention and replaces the continuous representation with a discrete approximation. Most neural surrogates accelerate the simulation, but inherit this representation gap by relying on meshes, point clouds, voxels, or other sampled approximations of geometry. We introduce CANTO, a
transformer neural operator that maps directly from continuous CAD geometry to physical fields, without meshing the input geometry. We develop a theoretical framework for learning operators from
geometric manifolds to function spaces of physical fields, representing geometry through sequences of parametric patches. CANTO instantiates this framework by directly tokenizing non-uniform rational B-spline (NURBS) patches from their control points,
knot vectors, and weights, and predicts continuous surface and volume fields at arbitrary query locations. We evaluate CANTO on four automotive and aircraft aerodynamics industry
benchmarks: AhmedML, WindsorML, DrivAerML, and HiLiftAeroML. CANTO achieves state-of-the-art accuracy on most evaluated surface and volume prediction tasks, including a 19.8% reduction in surface-pressure relative $L_2$ error compared with AB-UPT on HiLiftAeroML. Differentiability with respect to CAD parameters further enables gradient-based inverse design of designs. On AhmedML, CANTO identifies designs with 4.4 to 20.4% lower drag than the best
dataset designs satisfying the same volume and lift constraints, with the improvements verified using the same CFD setup used to generate the original
dataset.
Read the full abstract ▾
All authors Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn, Ruben Ohana, Ira J. S. Shokar, Abouzar Ghasemi, Semih Akkurt, Rishikesh Ranade, Neil Ashton, Jan Kautz, Jean Kossaifi
Artificial Intelligence
UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval
Mengkun Liang, Haoran Qiang, Guannan Liu et al. (+1 more)
Large
language model (LLM)
agents reuse external
memory to guide new tasks, but effective
retrieval requires learning which
memory sets improve execution. Such learning relies on costly outcome feedback: ordinary
retrieval observes only executed sets, while evaluating alternatives requires additional rollouts. We introduce UpliftMem, which learns
memory retrieval from set-level execution uplift relative to the same executor without
memory. A theoretical analysis of how
retrieval preferences restrict feedback coverage motivates targeted probing of alternative
memory sets. Probe selection follows an expected value of sample information (EVSI) criterion, derived in closed form under a correlated Gaussian model, to allocate limited training rollouts according to their expected improvement in local
retrieval decisions. The shared scorer is trained with a frozen executor and selects
memory sets without test-time probes. Across ALFWorld, WebShop, and BigCodeBench, UpliftMem achieves the best success rates among evaluated baselines on the main evaluation sets. Controlled fixed-store and matched probe budget evaluations further demonstrate improved
memory-use decisions and more effective use of execution feedback.
Read the full abstract ▾
All authors Mengkun Liang, Haoran Qiang, Guannan Liu, Junjie Wu
Computation and Language
VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction
Yitong Han, Nankai Lin, Juan Luo et al. (+3 more)
Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and grammatical errors but remain relatively underexplored. Existing LLM-based approaches face two recurring obstacles in this task: over-correction, and unclear interaction between Chain-of-Thought (CoT)
reasoning and self-consistency decoding, such that the benefits brought by CoT cannot be reliably transferred to final corrections. We propose Vote-guided Advantage Allocation for CSEC (VAA-CSEC), a multi-stage framework that combines CoT
distillation, Supervised Fine-Tuning (SFT), Reinforcement Learning (RL) and self-consistency decoding. During RL, we design a task-specific reward function that directly aligned with the minimal-editing principle of CSEC. We further introduce Group-Level Relative Policy Optimization (GLPO), which reallocates GRPO advantages according to the margin between individual rollout rewards and the vote-aggregated group reward, aligning the RL training objective with the self-consistency objective used at inference time. Experiments on CSED-C and NaSGEC-Exam show that VAA-CSEC outperforms all LLM-based baselines on CSED-C with an F0.5 of 47.72%, achieves the highest recall of 42.15% among all methods, and establishes a new state of the art of 41.55% F0.5 on NaSGEC-Exam.
Read the full abstract ▾
All authors Yitong Han, Nankai Lin, Juan Luo, Hongyan Wu, Lianxi Wang, Shengyi Jiang
Computer Vision
EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding
Yuwei Miao, Xuesheng Zhang, Wenhao Zou et al. (+5 more)
Real-time
video understanding requires incrementally maintaining a
memory of streaming content, and optimizing this requires dense process signals. On-Policy Self-
Distillation (OPSD), which lets one model serve as both teacher and student with the teacher receiving additional privileged information such as the question and ground-truth (GT) answer, can supply such
token-level signals. However, applying it directly to streaming
video raises two problems. (1) The student cannot be optimized end-to-end, where
memory is written before the question arrives, yet the teacher scores it with the question-and-GT privilege, misaligning their preferences. (2) Effective-entity
memory collapses, where the question-and-GT privilege makes the teacher favor only question-relevant entities, and
token-mean averaging over a
memory renders its signal invariant to how many entities that
memory covers, both driving
memory against the streaming need for diversity. To address these issues, we propose Event-Grounded Self-
Distillation (EGSD), which characterizes streaming
memory as an incremental update over verifiable Events (key visual entities, actions, and details) and targets the two problems on this basis. For problem (1), we adapt the OPSD signal into a multiplicative weight combined with the outcome reward; for problem (2), we re-weight the teacher with Events as privileged information to counter its question-relevance bias, and add an entity-coverage reward to supply the coverage preference the
token-mean teacher lacks. Extensive experiments on mainstream online and offline
benchmarks show EGSD achieves strong performance, reaching 79.8% on StreamingBench and 73.4% on the OVO-Bench Real-Time track, while
memory analysis shows effective-entity recall rises 17.4% at only 6.8% more
memory length.
Read the full abstract ▾
All authors Yuwei Miao, Xuesheng Zhang, Wenhao Zou, Jixia Zhang, Jianwei Lv, Bo Yuan, Junfeng Wang, Shiao Xie
Machine Learning
EasyPPO: Stabilizing the Critic Is Key
Xuanyi Zhou, Qiuyang Mang, Huanzhi Mao et al. (+7 more)
A key strength of Proximal Policy Optimization (PPO) is its learned critic, which uses historical trajectories collected during reinforcement learning to estimate expected returns and reduce policy-gradient variance. However, we find that the critic is also a major source of instability in reinforcement learning for large
language models (LLMs). We identify two critic failure modes that destabilize PPO. First, filtering truncated rollouts from both actor and critic shifts the policy objective to reward conditioned on completion, allowing truncation to increase even as conditional reward improves. Second, heterogeneous return noise can cause high-variance
prompts to dominate critic updates in finite batches. We introduce EasyPPO to address these failures. Actor-only overlong filtering trains the critic on returns from both completed and truncated rollouts. Noise-normalized critic regression weights each
prompt's critic loss by the inverse standard deviation of its sampled returns, balancing noise contributions across
prompts. Moderately smaller critic mini-batches confine outlier influence to fewer rollouts during gradient clipping. Across continuous-reward coding on FrontierCS, binary-reward mathematical
reasoning on AIME24, and multi-turn search on Search-R1, EasyPPO remains stable throughout the full training horizon and consistently outperforms vanilla PPO, VAPO, and HL-Gauss PPO. Its best validation scores show relative gains of 14.89%, 2.28%, and 9.47% over PPO, respectively.
Read the full abstract ▾
All authors Xuanyi Zhou, Qiuyang Mang, Huanzhi Mao, Dacheng Li, Wenhao Chai, Mayank Mishra, Yichuan Wang, Karthik Narasimhan, Alvin Cheung, Joseph E. Gonzalez
Computer Vision
Scene Retargeting: Learning Object Placement with Analogical Transfer
Minkwan Kim, Junho Kim, Seungmin Lee et al. (+2 more)
Interactive simulations of
embodied AI or spatial computing applications build on realistic 3D scenes that support daily activities. However, sparse, irregular layout structures impose scene-specific physical constraints, making it hard to define a generalizable framework for generating similar functional context. We formalize Scene Retargeting as stably transferring the semantically coherent spatial organization across layouts, rather than relying on textual descriptions or pairwise relationships. Our cluster-wise transfer flexibly handles mismatched object instances and adapts to distinctive floor plans. We optimize to preserve the rich semantic context of individual clusters by respecting the spatial distribution of foundation features. We can then impose physical constraints to refine wall contacts, pairwise
alignment, or clear passageways and openings. Our framework outperforms state-of-the-art methods on layout generation on the 3D-FRONT
dataset, and demonstrates downstream applications including real-to-sim transfer, analogical trajectory transfer, and multi-reference composition.
Read the full abstract ▾
All authors Minkwan Kim, Junho Kim, Seungmin Lee, Changwoon Choi, Young Min Kim
Artificial Intelligence
AI as a Compiler: Compiling Triton kernels without the Triton compiler
François Costa, Charly Castes, Thomas Bourgeat et al. (+1 more)
Compiler backends are expensive to build and maintain as programming models, workloads, and accelerators evolve. We investigate whether large
language models can replace the conventional optimizing and lowering pipeline, a process that we call AI lowering. We study AI lowering from Triton to NVIDIA PTX: an LLM
agent translates Triton kernels directly into PTX. We build an environment that evaluates candidate PTX, and an agentic harness in which an LLM translates Triton kernels into PTX. Across twelve common kernels on Ada, Hopper, and Blackwell GPUs and ten kernels from recent ML papers, AI lowering achieves 0.83x-3.34x the performance of autotuned Triton. The largest gains come from transformations that Triton's lowering pipeline does not perform, such as decoding packed binary weights directly into Tensor Core operands (3.34x on BitDelta), assigning each thread a complete softmax row in tensor
memory (1.37x on FlashAttention), and reusing overlapping convolution windows (up to 2.23x). These results rely on a robust evaluation harness with comprehensive verification support. We build on Volta, an existing PTX verifier, and substantially extend it to support modern GPU architectures by introducing support for Blackwell's tcgen05 Tensor Core interface. This requires modeling three architectural features: managed tensor
memory, descriptor-based operand layouts, and asynchronous execution coordinated through commits, waits,
memory barriers, and proxy fences. We discuss the challenges involved in formalizing them, as well as the current limitations. Our results suggest an emerging future in which AI compilers replace custom-written intermediate representations and checkers, reducing the time and engineering effort required to bring up software for new general-purpose and custom chips.
Read the full abstract ▾
All authors François Costa, Charly Castes, Thomas Bourgeat, Azalia Mirhoseini
Systems and Control
On a Class of Decentralized Feedback Controllers for the Networked Bivirus SIS Model
Sebin Gracy, Mengbin Ye and Brian D.O. Anderson
Recent work has established many properties of systems modeling the spread of two competing viruses in a population, and for networks with multiple connected populations with different spreading properties (e.g. men and women). This work considers the introduction of a class of nonlinear decentralized feedback controls aimed at reducing the fractions of populations infected at an endemic
equilibrium. One surprising conclusion is that in some circumstances, new types of
equilibria can arise. They can be viewed as an outcome of a transcritical bifurcation which is never observed for uncontrolled systems. In addition, we show that the controlled system is strongly monotone, and an unstable boundary
equilibrium of the uncontrolled system cannot be stabilized using the class of decentralized state feedback controllers considered in this paper.
Read the full abstract ▾
Computer Vision
Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs
Yueran Ma and Ronghao Lin
Omni-modal large
language models (LLMs) are expected to answer a question using the modality it explicitly refers to. However, existing training paradigms rarely verify whether models actually follow this modality, because
multimodal inputs from the same sample often provide redundant evidence for the same answer. In this work, we uncover a pervasive cross-modal shortcut in omni-modal LLMs: when asked an audio-related question, models rely on the image as much as on the audio, and sometimes even more. To systematically diagnose this behavior, we introduce the Factorized Modality Diagnostic, which independently swaps audio and images between samples to isolate each modality's causal contribution. Across two model families in different settings, we find that this shortcut persists throughout supervised fine-tuning and reinforcement learning post-training, while judge-based RL may further amplify such reliance on irrelevant visual information. Based on this finding, we propose DMC-Repair, which trains models on the same kind of cross-modal swapped samples while assigning supervision according to the modality specified by the question. This prevents models from exploiting the spurious correspondence between modalities within the same clip. Experiments demonstrate that DMC-Repair reduces the image-induced share of the answer effect by 59.9%, effectively suppressing the cross-modal shortcut without compromising audio-question answering performance. The reduction in shortcut reliance generalizes across two model families and zero-shot to an unseen
dataset and an unseen
benchmark, and persists through subsequent post-training. Code is available at https://anonymous.4open.science/r/DMC-Repair.
Read the full abstract ▾