Artificial Intelligence
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
Bo Mao, Hang He, Linting Wang et al. (+17 more)
Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of a broader agentic interaction system comprising the environment, task,
agent harness, and evaluator. Scaling environments in isolation, however, does not guarantee commensurate gains in model performance, because reliable learning signals depend on coherent interactions among all components of the agentic interaction system. To address this problem, we introduce WEFT (Whole-system
Evolution For Tool-use Post-training), which couples scalable agentic interaction system construction, execution-driven self-
evolution, and stable post-training. WEFT scales agentic interaction system construction across environment breadth, task complexity, and interaction diversity. Execution-driven self-
evolution iteratively uses execution traces and state evidence to attribute failures and revise the responsible components, with fresh rollouts evaluating the changes and providing evidence for subsequent
evolution rounds. For stable post-training at scale, WEFT addresses both optimization and execution reliability: prefix-preserving sampling retains verified progress and atomic-turn credit assignment localizes learning signals, while MegaMCP maintains isolated, recoverable state across concurrent rollouts over shared tool services. Extensive experiments across various models and
benchmarks demonstrate the effectiveness of WEFT for tool-use post-training. WEFT-8B and WEFT-14B outperform all evaluated matched-size environment-scaling baselines on BFCL V4, $\tau^2$-Bench, and Claw-Eval. In particular, WEFT-14B improves over
Agent-World-14B by 6.41, 2.23, and 12.27 percentage points. WEFT-35B-A3B further extends these gains to more challenging long-horizon workflow
benchmarks, including Toolathlon-Verified and AutomationBench.
Read the full abstract ▾
All authors Bo Mao, Hang He, Linting Wang, Lizhi Lin, Maosen Zhou, Guanming Liu, Jinxiu Liu, Tianyu Huai, Chaoyun Zhang, Bingxuan Li, Kepeng Lei, Guanting Dong, Zhou Shao, Rui Zheng, Hang Yan, Jie Zhou, Chengcheng Wan, Tao Gui, Liang He, Xipeng Qiu
Machine Learning · Cross-listed from q-bio.BM
RNA Design via Conditioned Flow Matching and Finite-Policy Reinforcement Learning
Zefeng Lin, Xianyong Fang, Tianfan Fu et al. (+1 more)
RNA design aims to identify sequences that fold into specified secondary structures. Existing methods formulate the task as target-specific search or conditional generation. However, natural RNA
evolution proceeds through sequence variation and selection, with compensatory substitutions, whereas these methods do not explicitly model this process. To address this limitation, we propose a two-stage framework comprising RNA Inverse-Folding Flow (RNA-IFlow) and RNA-IFlow-RL. RNA-IFlow uses structure-conditioned Dirichlet Flow Matching to model coordinated variation across the sequence, while RNA-IFlow-RL maps the learned flow to a pairing-preserving finite policy and refines it with thermodynamic feedback. Our framework achieves leading performance on multiple
benchmarks, reaching 85.19% Pass@1 on Rfam-27. Further analyses reveal thermodynamic gains, policy dynamics, and robustness across settings. Our work couples coordinated variation with thermodynamic selection, offering a novel paradigm for RNA design.
Read the full abstract ▾
All authors Zefeng Lin, Xianyong Fang, Tianfan Fu, Xiaohua Xu
Machine Learning
Architecture Alignment With Sparse Priors in Tabular Foundation Models
Tianqi Zhao, Tianyi Zhuang, Shuo Duan et al. (+3 more)
Tabular foundation models (TFMs) are increasingly popular because they deliver strong predictions on new
datasets through in-context learning, without task-specific training or extensive tuning. Yet released TFMs differ simultaneously in their pretraining priors, architectures, and objectives, obscuring their respective inductive biases. We therefore examine one concrete capability: irrelevant-feature suppression. Across synthetic tasks and real-world
datasets, adding null features causes substantially greater predictive degradation in the row-
token model TabDPT, whereas the
cell-
token alternating-axis model TabPFN v2 and other TFMs remain comparatively stable. This gap motivates us to ask whether architecture contributes to irrelevant-feature suppression. Because released TFMs remain confounded by other design choices, we train streamlined row-
token and alternating-axis
transformers under identical sparse-to-dense linear priors. Exact Bayes analysis shows that sparse prediction requires context-dependent feature gating, whereas the dense endpoint requires only uniform feature weighting. Consistent with this distinction, the alternating-axis model is substantially closer to the
Bayesian optimal predictor on sparse tasks, while the architecture gap becomes negligible on dense tasks; almost all of the sparse gap arises from linear coefficient-estimation error. Finally, in both the controlled model and frozen TabPFN v2, we examine the effect of interventions on the feature-
attention outputs on the linear coefficients, finding evidence of task-dependent selective routing of computation through feature-indexed pathways. Together, these results support architecture-prior
alignment: preserving an addressable feature axis provides an inductive bias for task-adaptive relevance inference. Code is available at https://github.com/Tianqi-Zhao/ArchitecturePriorTFMs.
Read the full abstract ▾
All authors Tianqi Zhao, Tianyi Zhuang, Shuo Duan, Guanyang Wang, Yan Shuo Tan, Qiong Zhang
Computer Vision
Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
Junhee Lee, Donghyeon Jeon, Taeoh Kim et al. (+2 more)
Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with semantic or object boundaries. Existing approaches rely on pixel-level supervision from controlled editing pipelines, which is difficult to scale and can introduce misleading signals: artifacts frequently extend beyond annotated regions, while out-of-mask pixels are treated as authentic. This limits models' ability to capture transferable evidence and generalize across generators and
datasets. To address these issues, we propose ReGFLoW, a Reconstruction-Guided Fake Localization framework under Weak supervision, which is the first weakly supervised approach for
diffusion-edited fake region localization. ReGFLoW requires only real/fake labels at the image level and uses
diffusion reconstruction errors as dense spatial guidance to inject them into both feature and score spaces. Furthermore, by artifact-centric multiple instance learning, ReGFLoW utilizes localized
diffusion evidence without relying on semantic-affinity or boundary-based pseudo-mask priors. Extensive experiments show competitive cross-generator localization, while ReGFLoW outperforms all evaluated fully supervised baselines when evaluation includes both partially edited and fully synthetic images and in cross-
dataset tests, without target-domain adaptation.
Read the full abstract ▾
All authors Junhee Lee, Donghyeon Jeon, Taeoh Kim, Beomyoung Kim, MyeongAh Cho
Machine Learning
What You Observe Determines How You Identify Causal Effects: Evaluating Causal Models across Observational Views
Heejin Jung, Gyeongdeok Seo, Hoyoon Byun et al. (+2 more)
Causal foundation models (CFMs) pre-trained on data generated from various structural causal models (SCMs) have been proposed for estimating causal effects from observational data. However, differences in pre-training environments and evaluation protocols make it difficult to assess how their performance depends on the information available for causal identification. To enable controlled comparisons, we introduce CausalIDView, a multi-view
benchmark that holds fixed SCM realization and target estimand while varying only the observational view available to the
estimator. Each observational view corresponds to a distinct identification regime under the
benchmark's maintained causal assumptions. Across these matched views, no CFM consistently performs best and model rankings vary substantially. Under controlled structural changes, CFMs exhibit model-specific failures to maintain stable estimates when true effects are unchanged and to track genuine effect changes. We also examine whether combining explicit identification with strong predictive estimation is effective. A modular approach that pairs a predictive tabular foundation model with regime-specific identification procedures is competitive with CFMs and outperforms several of them. These findings motivate cross-regime comparisons to assess the empirical value of CFMs.
Read the full abstract ▾
All authors Heejin Jung, Gyeongdeok Seo, Hoyoon Byun, Joseph Lee, Kyungwoo Song
Cryptography and Security
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
Haoran Ou, Gelei Deng, Xuanye Zhang et al. (+3 more)
As LLM-based
agents perform increasingly complex tasks,
Agent Skills have emerged as a flexible mechanism for extending their capabilities. An
Agent Skill packages task-specific instructions with executable components and auxiliary resources to provide specialized functionalities. However, the growing adoption of third-party Skills introduces a new supply-chain attack surface. Malicious Skills can embed harmful behaviors that abuse
agent privileges and compromise the
agent execution environment or accessible resources. Although recent LLM-based malicious Skill
auditing approaches have achieved promising performance, they often rely on capable commercial LLMs. How to achieve effective
auditing with compact, locally deployable LLMs in security-sensitive and resource-constrained settings remains largely unexplored. Our investigation reveals that compact LLMs struggle to identify malicious behaviors hidden in complex Skill packages. This difficulty arises from both the implicit nature of such behaviors and the limited
reasoning capacity of compact LLMs. To address these challenges, we propose SKILLLITE, an evidence-guided agentic framework for malicious Skill detection. SKILLLITE effectively extracts security-relevant behaviors and infers the intended functionality from complex Skill packages. It then employs a compact LLM to assess the maliciousness of the Skill based on the observed behaviors and their functional context. Experiments show that SKILLLITE improves malicious Skill detection across different compact LLM backbones and outperforms existing representative
auditing baselines. Its effectiveness generalizes to behaviorally confirmed in-the-wild malicious Skills. Meanwhile, SKILLLITE maintains a low inference latency, supporting its practical deployment.
Read the full abstract ▾
All authors Haoran Ou, Gelei Deng, Xuanye Zhang, Wenbo Guo, Tianwei Zhang, Kwok-Yan Lam
Robotics
NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction
Junjie Zhang, Jie Yin, Kefei Qian et al. (+5 more)
LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it or reproduce it using reconstruction methods that require real intensity supervision and per-scene optimization. These requirements increase data-collection and fitting costs and limit reuse across simulated scenes. We present NIDAR, a feed-forward framework that synthesizes dense intensity-like observations from RGB appearance and simulator geometry. NIDAR combines pretrained pseudo-NIR translation, hierarchical intrinsic decomposition, geometry-aware modulation, and source-domain distribution calibration to transfer reflectance-related image cues to simulated point clouds. Its learned components are trained offline using Waymo data; their weights and calibration remain fixed during evaluation on Waymo and nuScenes. Deployment therefore requires neither target-scene intensity labels nor target-scene gradient-based fitting. The reported comparisons show competitive pixel-wise accuracy and favorable structural and perceptual fidelity against the evaluated reconstruction baselines. A controlled pseudo-NIR-versus-RGB diagnostic further shows that the pseudo-NIR prior is most beneficial when used through the paper-aligned reflectance-and-remapping route, rather than as a simple direct intensity regressor. We further integrate NIDAR with Unreal Engine 5, Isaac Sim, and a generative
LiDAR pipeline. Two intensity-aware SLAM systems evaluated in two simulated indoor scenes suggest potential downstream utility, but do not constitute real-
robot validation. NIDAR therefore offers a scalable intensity-synthesis interface for the evaluated settings; cross-wavelength, camera-configuration, embedded, and real-sensor validation remain future work.
Read the full abstract ▾
All authors Junjie Zhang, Jie Yin, Kefei Qian, Jie Li, Mengpei Jia, Yajuan Dun, Wenbo Chu, Guofa Li
Computer Vision
S4VY: Segment Anything in Feed-Forward 4D Visual Geometry
Jingdong Zhang, Xin Li, Jan Kautz et al. (+2 more)
Accurate instance
segmentation in dynamic scenes is important for downstream applications such as robotics and autonomous driving. Existing Segment Anything models operate primarily on 2D image or
video masks and preserve identity through sequential
memory, while promptable 4D instance
segmentation built upon feed-forward visual geometry remains underexplored. We introduce S4VY, a Segment Anything model built on feed-forward 4D visual geometry. From a set of RGB observations, S4VY transforms shared visual-
geometric features into an exhaustive set of class-agnostic 4D instance masks through a space-time query decoder, with each persistent object query binding one entity across all observations. This representation supports
prompt-independent
segmentation as well as point- and box- conditioned selection, without requiring a seed mask or temporal ordering. We further develop an agentic harness for natural-
language grounding in the large observation space of a 4D scene. Active tree search identifies relevant frames without scanning every fixed window; a dual-stream grounder combines fine-grained VLM visual priors with geometry-consistent instance features through complementary bounding-box prediction and object-query matching; and an independent critic selects the final 4D instance mask from their predictions. Extensive experiments demonstrate state-of-the-art 4D instance
segmentation and strong
language-guided grounding performance under a unified evaluation spanning static and dynamic scenes.
Read the full abstract ▾
All authors Jingdong Zhang, Xin Li, Jan Kautz, Wenping Wang, Chris Choy
Machine Learning
Seeing Time: Visual-Temporal Representation Learning for Interpretable Time Series Clustering
Zheng Zhu, Zexi Tan, Yuming Deng et al. (+1 more)
Multivariate Time Series (MTS) clustering is an important tool in temporal data mining, aiming to discover latent group structures from complex observations without supervision. Although existing deep clustering methods can learn discriminative temporal representations, the resulting latent clusters are often difficult to relate back to waveform characteristics that practitioners can directly inspect and compare, limiting their ability to assess whether the discovered patterns reflect meaningful temporal behaviors. This paper, therefore, proposes WAVE (Waveform Aligned Visual-temporal
Embedding), which treats time series and their deterministically rendered waveform plots as complementary views of the same observations. To produce discriminative representations whose cluster structures can be traced to observable waveform characteristics, WAVE aligns and integrates fine-grained temporal variations with holistic visual patterns, while associating each discovered cluster with its centroid-nearest authentic sample. Accordingly, interpretability in this work specifically refers to waveform-level traceability rather than a general explanation of model decisions. Extensive evaluations across 10 real-world public
datasets show that WAVE achieves the highest macro-averaged clustering performance and the best average rank among the compared methods, while qualitative case studies illustrate how the discovered clusters can be inspected through authentic waveform records. The source code is available at https://github.com/Zheng-Zhu1/WAVE.
Read the full abstract ▾
All authors Zheng Zhu, Zexi Tan, Yuming Deng, Yiqun Zhang
Robotics
PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions
Yiqi Tang, Diyuan Shi, Runze Li et al. (+1 more)
Flow-matching policies can represent complex
robot behaviors but remain susceptible to local errors under distribution shift at deployment. Many reinforcement learning approaches to policy improvement require reward signals that are difficult to specify or obtain in real-world manipulation. We present PreferenceFlow, a framework for improving a pretrained flow policy at test time without environment rewards or updates to the base policy. Human intervention chunks are paired with
robot chunks generated from the same initial conditioning state to train a preference model. During infer- ence, we adopt the QGF sampling update, replacing its value gradient with the preference gradient evaluated at an estimated clean action. A gradient-cap loss penalizes excessive gradients on intervention pairs, while a zero-gradient loss discourages guidance near actions from expert demonstrations. On four real-world precision insertion tasks with a Franka
robot, Pref- erenceFlow achieves a mean success rate of 90.5%, compared with 69% for the frozen policy. Ablations support the roles of gradient regularization and correctly ordered preference labels in the evaluated settings. These results demonstrate the utility of human interventions as local preference supervision for guiding frozen generative
robot policies.
Read the full abstract ▾
All authors Yiqi Tang, Diyuan Shi, Runze Li, Donglin Wang
Robotics
VidAct: Learning Manipulation from In-the-Wild Videos with Object-Centric 3D Awareness
Hang Li, Mingxin Zhang, Zihan Wu et al. (+9 more)
Video demonstrations offer a scalable alternative to costly
robot data for learning manipulation, yet existing reconstruction-based approaches often rely on constrained camera viewpoints or human-to-
robot retargeting, while the reconstructed trajectories are difficult to adapt to new objects configurations without distorting the trajectory shape. Another key limitation is that the resulting policies often lack precise object-level 3D geometry awareness, limiting object grounding and object shape awareness critical for precise manipulation. To bridge these gaps, we propose VidAct, an efficient
video-to-
robot framework that learns object-centric, 3D-aware manipulation policies from a single
monocular video per task and enables zero-shot real-world deployment. VidAct consists of three key components. First, VidAct reconstructs object meshes and motion from arbitrary demo
videos and canonicalizes the motion in the static object frame, avoiding embodiment-specific retargeting and accommodating diverse camera viewpoints. Second, VidAct employ residual trajectory transfer for adapting the reconstructed motion to novel object configurations while preserving its motion shape. Finally, as the key policy-learning component, VidAct predicts simulation-provided privileged complete-object point clouds at each frame as an auxiliary task while retaining RGB-only deployment, providing dense object-centric supervision over both object pose and 3D geometry. Experiments on human,
robot, generated, and internet
videos demonstrate broad
video applicability and zero-shot deployment. Per-frame complete-object 3D supervision improves policy generalization and sim-to-real success, while residual trajectory transfer enables reliable trajectory adaptation with better shape preservation.
Read the full abstract ▾
All authors Hang Li, Mingxin Zhang, Zihan Wu, Yang Tian, Dong Chen, Fengyi Shen, Yuan Meng, Xiangtong Yao, Heng Zhang, Ziyuan Liu, Zhenshan Bing, Alois Knoll
Artificial Intelligence
State Trace Rationale As Auxiliary Task in Reinforcement Learning
Muhammad U. Nasir, Alex Vogt, Steven D. James et al. (+1 more)
We propose STRAT, an auxiliary task that trains deep reinforcement learning (RL)
agents to predict a short textual trace of their own state. Inspired by human spatial
navigation, the description combines landmark, route, and survey knowledge, tracking the
agent's position, inventory, goals, and immediate progress. Environment rules generate this text online without human labelling. Our method adds a single auxiliary head to a standard policy. Across 60 sparse-reward XLand-MiniGrid tasks, STRAT solves complex environments where standard RL fails outright, while compacting state representations and preventing rank collapse. Beyond performance gains, the predicted trace provides a readable account of
agent beliefs at every step for no extra cost.
Read the full abstract ▾
All authors Muhammad U. Nasir, Alex Vogt, Steven D. James, Julian Togelius
Computer Vision
S2T-Unet: A Structure-to-Style Framework for Inter-Modality MRI Translation
Yichao Liu
Inter-modality MRI translation aims to synthesize missing MRI modalities from available acquisitions, reducing the need for additional scanning while preserving clinically relevant anatomical information. However, existing image translation methods often learn intensity mappings without explicitly separating modality-invariant structural information from modality-specific appearance, which may lead to structural information loss or unrealistic image details. In this work, we propose S2T-Unet, a structure-to-style framework that explicitly models these two aspects. Specifically, vector quantization is introduced at the lower-level bottleneck to encode modality-invariant structural information using a learned discrete codebook. At higher levels, a modality transformation module uses decoder features to condition and transform encoder representations toward the target modality, thereby recovering modality-specific intensity and contrast information. Experiments on the IXI multi-contrast MRI
dataset across four translation tasks demonstrate that S2T-Unet is comparable or outperform with state-of-art method.
Read the full abstract ▾
Machine Learning
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
Fanchao Chen, Hengyu Fu, Shivaram Venkataraman et al. (+1 more)
Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling complete trajectories is costly and does not explicitly explore the decision space at critical positions. Feedback on a completed trajectory can reveal which earlier choices the policy reconsiders, suggesting where to sample alternative continuations. We introduce Hindsight-Divergence Localization (HDL), which uses hindsight-induced changes in
token log-likelihoods to select branch points. HDL generates a small number of complete root trajectories and fills each training group with continuations from the selected positions under the original task context. Each continuation reuses its root prefix and contributes policy updates only through its newly generated suffix, reducing generation cost while focusing additional exploration and learning on decisions after branching. Experiments with three models across math, code, and
agent tasks show gains in both rollout efficiency and task performance. Compared with GRPO at matched group sizes and training steps, HDL yields up to a 2.5$\times$ reduction in generated
tokens and a 1.8$\times$ speedup in rollout wall-clock time. Despite this reduced generation budget, HDL improves performance across all three domains, with gains of up to 12.5 points on
agent tasks.
Read the full abstract ▾
All authors Fanchao Chen, Hengyu Fu, Shivaram Venkataraman, Jiantao Jiao
Cryptography and Security
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu et al. (+2 more)
Fine-tuning-as-a-service lets users adapt a safety-aligned
language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of harmful data mixed into an otherwise benign fine-tuning set can degrade the model's
alignment. Two recent
alignment-stage defenses address this problem at different levels of the model. Vaccine improves the robustness of hidden
embeddings to the representation shifts induced by harmful fine-tuning, whereas Booster simulates harmful weight updates and attenuates their effect during
alignment. We investigate whether these mechanisms are complementary and propose VaccineBooster, a single
alignment procedure that combines
embedding perturbation and weight-level gradient attenuation within each training step. On Llama-2-7B aligned with BeaverTails and then attacked through poisoned fine-tuning, VaccineBooster achieves the lowest OpenAI moderation score among the compared defenses, 0.315, while a Booster-Only variant retains the highest post-attack refusal rate, 50%. Together with ablations over the
embedding-perturbation and gradient-attenuation strengths, these results indicate a trade-off:
embedding perturbation primarily reduces flagged harmful content, whereas gradient attenuation primarily preserves explicit refusal behavior. Because our evaluation uses ten
prompts and a single unseeded run per configuration, we report this trade-off as an observed pattern rather than a statistically resolved effect. These results provide practical guidance for prioritizing content safety or refusal retention when aligned models are exposed to untrusted fine-tuning.
Read the full abstract ▾
All authors Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu, Ali Zain Kaimkhani, Minghong Fang
Artificial Intelligence
IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence
Changdi Yang, Fengquan Jiao, Haochih Lin et al. (+14 more)
We present IronLLM-0.6B, a 654M-parameter
language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid
attention architecture with X-MTP, a lightweight shared-KV multi-
token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback-free drafting, achieving a 1.48x decoding speedup. The model is pretrained on approximately 6.2 trillion
tokens using a quality-oriented data pipeline and is further post-trained with Multi-Domain On-Policy
Distillation to integrate capabilities from domain-specialized teachers. To better meet the low-latency requirements of on-device scenarios, IronLLM-0.6B adopts an Instruct-Only design. Evaluations show that IronLLM-0.6B achieves competitive performance relative to larger models such as Qwen3.5-0.8B and MiniCPM5-1B, while producing more concise responses on many tasks. We further present IronLLM-0.6B-Light, which replaces RMSNorm with Dynamic Tanh and simplifies several computationally expensive components to improve inference and quantization efficiency. Together, the IronLLM models provide an effective performance-efficiency trade-off for resource-constrained deployment.
Read the full abstract ▾
All authors Changdi Yang, Fengquan Jiao, Haochih Lin, Haoran Yang, Jing Xiao, Liangyu Huo, Suxin Lu, Tiance Chen, Wei Liu, Yinggan Xu, Yunxiang Lu, Zai Zheng, Zhirui Xie, Zhongyang Che, Ziyan Tang, Zuoxiang Zhao, Jian Yao
Machine Learning
Markovian Nonconvex ADMM for Reinforcement Learning: Bellman-Resolvent Stability Beyond Smooth Blocks
Zhaojun Peng
We identify and study a structural mechanism for Markovian nonconvex ADMM in reinforcement learning. Using finite discounted MDPs as a canonical proving ground, we show that the discounted Bellman resolvent $(I-\gamma P_\pi)^{-1}$ can provide the multiplier stability that classical nonconvex ADMM analyses often obtain from a designated smooth block. Starting from this mechanism, we establish convergence under controlled Markov sampling and then under
stochastic observations using an empirical Bellman surrogate that jointly represents the random residual and its Jacobian. Markov mixing, initialization drift, observation noise, and decaying bias enter as one operator perturbation, avoiding unbiased product and double sampling requirements. When the perturbations are square summable, the true KKT residual converges almost surely to zero. Under a finite conditional fourth moment condition, a companion iterate satisfies $ \mathbb{E}[\widetilde G_{K+1}] \le A/T+(B/T)\sum_{k<T}m_k^{-1}, $ which becomes $O(T^{-1}+T/N)$ for total Markov sample budget $N$, giving $O(\epsilon^{-1})$ iteration complexity and $O(\epsilon^{-2})$ sample complexity for squared KKT accuracy $\epsilon$. Beyond stationarity, discounted occupancy coverage yields $J^\star-J(\pi)=O(\sqrt G)$ for direct tabular policies, so covered exact KKT points are globally optimal, while a statewise quadratic Bellman-improvement condition sharpens the relation to $O(G)$. Finally, nonlinear policy, projected Bellman, and explicit occupancy formulations exhibit the same chain of operator invertibility, dual representation, and multiplier stability. This supports discounted operator invertibility as a reusable structural principle for primal-dual reinforcement learning.
Read the full abstract ▾
Systems and Control
Receding Horizon Control and Dissipativity - Optimal Control, Games and Uncertainty
Sophie Hall, Jonas Schießl, Sergio Grammatico et al. (+1 more)
We provide a tutorial overview of receding horizon control across deterministic,
stochastic, multi-
agent, and game-theoretic settings. We contrast the minimizer of an optimal control problem with the
equilibrium of a game in terms of cost and constraint handling to motivate the difference of MPC schemes involving multiple
agents/players. Interestingly, dissipativity theory and the turnpike property have turned out to be a unifying thread and system-theoretic backbone across all these schemes. This paper is the first to give an overview of results, summarizing fundamental insights, drawing parallels, and highlighting technical differences in dissipativity and turnpike analysis across economic, game theoretic, and
stochastic settings. We also explore recent trends in numerical methods for games. We conclude by pointing to a list of open challenges.
Read the full abstract ▾
All authors Sophie Hall, Jonas Schießl, Sergio Grammatico, Timm Faulwasser
Computational Engineering
FinRegQA-EU: Corruption-Based Preference Data for Grounded EU Financial Regulatory Question Answering
Aulia Kharis Rakhmasari, Fan Yu, Alexander Hoyle et al. (+1 more)
Large
Language Models (LLMs) struggle with region-specific factual knowledge, particularly in financial regulation. While
benchmarks such as CFinBench, provide broad coverage of financial knowledge in other regions, no comparable resource exists for European financial regulation. We close this gap by proposing an end-to-end pipeline for evaluating and improving LLMs on European financial regulatory question answering. Our
dataset is grounded in the official Q&A corpora of the European Banking Authority (EBA) and the European Securities and
Markets Authority (ESMA). We evaluate candidate answers with a pointwise LLM-as-a-Judge protocol using three judges from distinct model families, retain only unanimously judged pairs, and sharpen the rejected side through a taxonomy of regulatory failure modes : law swaps, article swaps, hallucinated citations, and hallucinated text. By fine-tuning on the resulting preference pairs exposes a divergence at the core of our findings: supervised fine-tuning attains the highest judge score of any method yet got the lowest rule-based Citation F1. SFT is producing longer answers with three times as many citations, most of them unsupported. DPO and GRPO offer the better trade-off with more concise answers and the highest citation F1 among fine-tuned models. Standard LLM-as-a-Judge evaluation rewards citation density as evidence of grounding and cannot detect when those citations are fabricated. Thus, we detect a blind spot that matters wherever answers must be verifiable. We release the
benchmark and evaluation stack at https://github.com/auliakharis/FinRegQA-EU.
Read the full abstract ▾
All authors Aulia Kharis Rakhmasari, Fan Yu, Alexander Hoyle, Elliot Ash
Artificial Intelligence
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Yaxin Gong, Gangyi Zhang, Chongming Gao et al. (+7 more)
Multi-
agent LLM systems rely on message passing among specialized
agents to accomplish complex tasks. However, an upstream
agent may provide useful information or an incorrect answer that causes a downstream
agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five
benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream
agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream
agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream
agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream
agent copies the upstream's specific wrong answer–a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream
agent.
Read the full abstract ▾
All authors Yaxin Gong, Gangyi Zhang, Chongming Gao, Leyang Shen, Chenxiao Fan, Jiakai Wang, Dong Wang, Yang Liu, Wenjie Wang, Xiangnan He
Computer Vision
Socialality Anchors: Towards Group-bounded Trajectory Prediction
Ziqian Zou, Conghao Wong, Qinmu Peng et al. (+1 more)
Trajectory prediction is a key component for understanding human behavior patterns in dynamic scenes. Researchers have devoted substantial efforts to modeling social interactions, especially group-wise interactions, since group membership often reflects shared intention, coordinated motion, and stable mutual adaptation, thus providing a persistent and semantically meaningful social prior for
forecasting. However, existing group modeling methods may rely on a fixed threshold and infer groups mainly from
agents' relative positions within the observation window, overlooking the fact that grouping rules should be
agent-specific, temporally coherent, and context-adaptive across diverse personalities, culturalities, and evolving interaction contexts. Inspired by human social perception that alternates between interpersonal distance in boundary-sensitive situations and relative speed consistency in dynamic interactions, we propose Socialality, a human-inspired trajectory prediction framework with interpretable Socialality anchors and an extended grouping window for stable, context-aware grouping inference. Concretely, Socialality introduces a duo-scalar-controlled grouping kernel Socialality that jointly leverages historical observations and short-term future trajectory previews to learn
agent-specific grouping rules, and employs a group-wise perception mechanism to model in-group and out-of-group interactions in an intuitive and explainable manner. Furthermore, we conduct extensive experiments on standard
benchmarks to demonstrate the performance gains of Socialality, and provide qualitative analyses and statistical studies of anchor distributions to verify the interpretability and stability of the proposed Socialality anchors.
Read the full abstract ▾
All authors Ziqian Zou, Conghao Wong, Qinmu Peng, Xinge You
Computer Vision
RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
Hongbin Lin, Chaoda Zheng, Yiming Yang et al. (+11 more)
End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their own actions, leading to causal confusion in closed-loop real-world deployment. To address this issue, reinforcement learning (RL) post-training offers a promising alternative by leveraging world models as interactive training environments to enable future scene generation for policy improvement. Nevertheless, existing approaches either rely on reconstruction-based simulators, offering limited counterfactual interaction, or adopt synthetic simulators to enable long-horizon closed-loop interaction at the cost of a substantial sim-to-real gap. Recently,
video world models have exhibited the ability to generate realistic multi-step future rollouts but may not faithfully reflect action conditions, resulting in action-
vision mismatch. In this paper, we introduce RoXDrive, a plug-and-play closed-loop RL framework that enables reliable policy optimization by identifying action-faithful world-model rollouts, consisting of two stages: 1) Model pre-training: In addition to imitation-based policy pre-training, we devise an Action-
Vision Faithfulness Evaluator for inverse dynamics estimation with our geometry-aware auxiliary trajectory supervision, enabling long-horizon assessment of whether visual dynamics faithfully reflect the conditioning ego actions. 2) Action-faithful RL post-training:
Agents iteratively interact with world models to form long-horizon scene rollouts, retaining only action-faithful ones for dense safety-aware scoring and scene-level closed-loop RL post-training. Extensive experiments on nuScenes and an in-house
dataset with over 130K training scenarios demonstrate consistent gains across planners, reducing safety violations by 27.6% with DiffusionDrive on nuScenes and 33.7% with Qwen3-VL on the internal data.
Read the full abstract ▾
All authors Hongbin Lin, Chaoda Zheng, Yiming Yang, Xiangyu Li, Shijia Chen, Jinhao Deng, Kangjie Chen, Dongbin Zhang, Jie Feng, Yu Zhang, Xianming Liu, Shuguang Cui, Boyang Wang, Zhen Li
Computation and Language
Rethinking Multimodal Fake News Detection in the Generative AI Era
Wenbin Shen, Guoxuan Qin, Guangxu Yao et al. (+3 more)
Generative content is increasingly entering the production and dissemination of news, transforming fake news from manually fabricated or simply manipulated material into complex forms in which native and generated content jointly participate. Existing
multimodal fake news detection research primarily focuses on veracity assessment and rarely characterizes how generativity differences affect the reliability of evidence. In contrast, AIGC detection primarily determines whether content is generated or modified by generative models, but it does not by itself establish whether the underlying news event is true. To bridge the separation between these tasks in data and evaluation, we construct Weibo26, a
multimodal fake news detection
dataset for generative-content scenarios. On this basis, we propose the Generativity-Aware Hierarchical
Reasoning (GAHR) framework, which combines global judgment with local correction so that generativity information participates in news-veracity
reasoning. Experiments on multiple existing fake news detection
benchmarks and Weibo26 show that GAHR achieves competitive veracity-detection performance while effectively identifying generative content.
Read the full abstract ▾
All authors Wenbin Shen, Guoxuan Qin, Guangxu Yao, Baodong Wang, Yuanbo Rui, Zhichao Lian
Cryptography and Security
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
Omar Sheta, Rinku Deuja, Hadi Masoudi et al. (+1 more)
Safety-aligned
language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single
prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single
prompts: they score an input by the
alignment between its induced gradient and a fixed unsafe reference direction, and their effectiveness in multi-turn dialogue remains unclear. We conduct a controlled evaluation of gradient-based jailbreak detection in multi-turn settings. We extend GradSafe with a Context Window Scanner that applies the detector to fixed-size windows of user turns and uses the maximum window score as the conversation-level score. We evaluate different window sizes, attack families, benign conversation distributions, and target models. The results differ sharply between synthetic and realistic benign settings. Against synthetic benign conversations, the detector achieves an ROC-AUC of 0.98 on human-authored multi-turn jailbreaks. On WildChat benign conversations, ROC-AUC drops to 0.76, and a threshold calibrated on synthetic data flags more than 90% of benign conversations as unsafe. Under realistic benign distributions, single-turn windows give the highest separability, whereas longer windows and accumulated contexts reduce performance. The detector is also sensitive to the attack-generation method and target model: successful Crescendo attacks receive scores comparable to or lower than benign conversations, and Qwen2.5-7B-Instruct yields near-random separability with a different optimal window size. These findings show that gradient-based signals can support multi-turn jailbreak detection, but reliable deployment requires calibration on realistic benign conversations, short-window scoring, length-aware thresholds, and evaluation across attack types and model architectures.
Read the full abstract ▾
All authors Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang
Machine Learning
An Effective, Reliable, and Robust Framework for Human Activity Recognition Using Wearable Sensors
Nafees Ahmad, Ho-fung Leung, Muhammad Adil Abid et al. (+1 more)
Human Activity Recognition (HAR) through wearable sensors greatly improves the quality of human life through its multiple applications. For HAR, multi-sensor channel information is vital for optimal performance. Current work states that applying an
attention neural network to prioritize discriminatory sensor channels helps the model classify activity more precisely. However, obtaining discriminatory information from multisensory channels is not always trivial, such as when collecting data from older hospitalized patients. In this context, existing HAR methods struggle to classify activities, particularly activities with similar natures. Moreover, HAR models predominantly suffer from overfitting due to the small size of available
datasets, which leads to poor performance. Data augmentation (DA) is a viable solution to this problem. However, available DA methods have various drawbacks, including the possibility of being domain-dependent, resulting in distorted models for test sequences. To address these HAR problems, we propose a novel framework, ALAE-TAE-CutMix+, which focuses on two aspects. First, it enhances the latent information across each sensor channel and learns to exploit the relation among multiple latent features and the ongoing activity. Consequently, the discriminatory feature representations of each activity is enriched. Second, a new augmentation strategy is introduced to address the shortcomings of existing multi-sensor channel data augmentation. We then extend the framework to create a further enhanced version, namely ALAE-CIE-TAE-CutMix+, which learns to capture the interactions between the features of each pair of sensor channels. We find that although the first framework performs slightly better than the latter, the latter is nonetheless more reliable and robust. Both frameworks significantly outperform SOTA approaches on the four HAR
datasets from diverse domains.
Read the full abstract ▾
All authors Nafees Ahmad, Ho-fung Leung, Muhammad Adil Abid, Sadia Shakil
Artificial Intelligence
Automated Screw Planning for Reduced Pelvic Fractures Based on Statistical Shape Models and Deep Learning
Yang Gao, Sutuke Yibulayimu, Yanzhen Liu et al. (+2 more)
Percutaneous iliosacral screw fixation is an important minimally invasive treatment for unstable pelvic fractures. Because the sacroiliac region has complex anatomy and narrow screw corridors, the accuracy and safety of screw placement directly affect
surgical outcomes. Accurate and reliable preoperative screw planning is therefore essential to improve
surgical success and reduce intraoperative risks. Conventional preoperative planning typically requires surgeons to determine screw trajectories through manual measurements, a labor-intensive process that depends on subjective clinical experience. To address these challenges, we propose a fully automated pipeline for preoperative iliosacral screw planning in patients with pelvic fractures. Using patient-specific three-dimensional anatomy, the pipeline automatically identifies safe screw corridors and generates individualized insertion trajectories to support clinical preoperative planning. We evaluated the proposed pipeline on 200 clinical cases of pelvic fractures. Compared with conventional manual measurements, the safety margin of the safe insertion corridors increased by 2% across the four screw types, the mean planning time decreased by more than 90%, and the clinical acceptance rate reached 95%.
Read the full abstract ▾
All authors Yang Gao, Sutuke Yibulayimu, Yanzhen Liu, Zian Zhao, Yudi Sang
Networking
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen et al. (+4 more)
Uncrewed aerial vehicle base stations (
UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-
entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $\rho=0.95$. On a unified pipeline over three real
datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every
dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.
Read the full abstract ▾
All authors Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen, Xianbin Cao, Xinmei Qiang, Dapeng O. Wu, Tony Q. S. Quek
Computer Vision
GlassFormer: Learning Real-time Glass Segmentation using Radar-Depth Fusion
Suhani Grover, Astik Srivastava, Viswas Dinesh et al. (+2 more)
Transparent surfaces are ubiquitous in built environments, yet they remain a persistent failure case for robotic perception. RGB cameras perceive the background behind glass rather than the surface itself, while depth sensors such as
LiDAR, time-of-flight, and RGB-D often return invalid or background measurements in transparent regions. As a result, systems that rely solely on optical sensing may misinterpret glass walls, doors, or mirrors as free space, compromising safe and reliable
navigation. Existing glass
segmentation approaches address this by learning visual cues such as reflections, boundaries, and semantic context from RGB images. While effective under favourable lighting and viewing conditions, these cues degrade in low-light environments, under glare, or when glass surfaces are featureless or partially occluded. In this work, we propose a
multimodal framework that fuses millimetre-wave radar with RGB-D sensing for real-time transparent surface
segmentation. Radar reflects strongly off glass surfaces, providing a
geometric cue that remains reliable precisely where
vision and depth fail. We exploit this cross-modal inconsistency to generate a radar-guided spatial prior, which is integrated into a lightweight
transformer-based
segmentation network, GlassFormer, via cross-modal
attention. We report results on a mixed-condition test split covering all scene types and a dedicated low-light split designed to stress
vision-only methods. GlassFormer achieves 0.88 mIoU on the mixed split, and 0.59 mIoU on the low light split, demonstrating substantial robustness gains over
vision-only baselines while maintaining real-time performance on resource-constrained platforms.
Read the full abstract ▾
All authors Suhani Grover, Astik Srivastava, Viswas Dinesh, Avinash Sharma, K. Madhava Krishna
Machine Learning
RolloutFaith: Auditing Persistent Internal Interventions in Visual World Model
Junchi Yao, Ziyi Wang, Youling Huang et al. (+1 more)
Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World models pose a harder requirement: because their predictions become inputs to later predictions, a useful internal correction must survive after editing stops. We therefore propose RolloutFaith, a framework that measures semantic improvement both in the prediction produced at intervention time and over later autonomous predictions under fixed events, actions, noise, and information budgets. We evaluate ten fitted editors on three world models across Crafter, Cartpole, and CoinRun. We also use Reference Activation Patching, which replaces a model activation with the paired activation computed from the real observation, to measure the correction available at the chosen interface. This reference intervention improves later predictions in all nine model and task combinations and outperforms the best fitted editor in eight, yet its sustained gain decreases with horizon in five of nine combinations. Current fitted editors recover only limited and inconsistent long term effects. By restoring individual state components to their untouched values, we find that persistent effects travel through the newest generated frame in DIAMOND, recurrent
memory in DreamerV3, and both in STORM. These findings suggest that training should reward future consequences. To test this hypothesis, we propose Delayed LoReFT, which optimizes the same low rank intervention through four frozen future transitions and improves sustained intervention effects to some extent.
Read the full abstract ▾
All authors Junchi Yao, Ziyi Wang, Youling Huang, Lijie Hu
Computer Vision
Does the VGGT Family Need All Its Layers?
Fengyi Zhang, Holger Caesar, Xiangyu Sun et al. (+3 more)
Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, $\pi^3$, and VGGT-$\Omega$: 3,018 pruned configurations, scored on seven camera-pose and dense-geometry metrics across four indoor and outdoor
datasets. Four findings follow: (i) Removable layers cluster in two redundancy regions: a dominant early region and a narrower late one, while deletions spanning the intervening layers are consistently more disruptive. This recurring pattern holds across models,
datasets, and metrics, and contrasts with the middle-to-late redundancy commonly reported in the literature. (ii) Within these regions, we observe that the joint degradation from deleting two intervals is approximately the sum of their individual degradations, reducing the number of model evaluations for
pruning search from $O(L^4)$ to $O(L^2)$, where $L$ is the aggregator depth. (iii) We find that CKA provides a cheaper representation-based proxy for interval degradation, offering a practical trade-off between
pruning quality and calibration cost. (iv) Closed-form linear calibration recovers accuracy after
pruning without end-to-end retraining. A least-squares analysis shows that using a shared map for special and patch
tokens generally incurs excess reconstruction loss, motivating
token-aware recovery. Recovery maps fitted on just 100 calibration scenes generalize to held-out scenes and unseen
datasets. The resulting models reduce aggregator parameters by up to 44% while maintaining accuracy comparable to their intact counterparts. Code and experimental results will be available at our project page: https://xian-bei.github.io/vggt-family-layer-redundancy/
Read the full abstract ▾
All authors Fengyi Zhang, Holger Caesar, Xiangyu Sun, Zheng Zhang, Zi Huang, Yadan Luo