Machine Learning
Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast
Jiajing Hu, Xu Han and Li-Ping Liu
Accurate uncertainty quantification is critical for many time series forecasting applications, and recent studies have increasingly adopted generative models to capture predictive uncertainty. Existing approaches often combine deterministic forecasting with generative modeling to improve predictive performance. However, their joint training is typically unstable because the deterministic model is embedded within the generative process, resulting in deep computational graphs and changing the probability transport path. In this work, we propose DV-Flow, a unified flow-matching formulation that incorporates the deterministic predictor as a parallel velocity component rather than as the endpoint of the transport path. This design enables stable end-to-end optimization while subsuming several existing formulations as special cases, allowing direct comparisons among them. Extensive experiments on six real-world
datasets demonstrate that DV-Flow consistently improves probabilistic forecasting performance over strong baselines. Our code is available at https://github.com/tufts-ml/dv-flow-time-series.
Read the full abstract ▾
Artificial Intelligence
Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
St John Grimbly, Nicolas Kuske, Evert A. Boonstra et al. (+6 more)
An embodied
agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of information about that need or by increasing its preference for outcomes that relieve it. We compare these two interventions, separately and together, in a foraging gridworld with three lethal needs, and ask how each changes survival, perception and the body model the
agent learns. Precision sharpens interoceptive posteriors and improves survival. Preference reweighting keeps bodily states further from their lethal boundaries and changes the states from which the
agent learns, so its learned model covers fewer need levels, with lower quality across all levels but slightly higher quality on the levels it visits. An experiment on 72 further layouts does not establish the predicted preference benefit on difficult layouts, but both interventions improve average survival there and their interaction is positive. Survival alone therefore gives an incomplete account of how a model prioritises needs and learns about its body.
Read the full abstract ▾
All authors St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms, Jonathan P. Shock
Computation and Language
Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve
Yuyang Bai, Yu Wang and Yu Zhang
Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence
agents can access, even when they write code to combine tool calls or process retrieved subgraphs. We propose direct knowledge graph interaction (DKGI), a harness in which
language model
agents create graph access tools directly over complete node and edge files. The
agent writes Python code to follow relations, combine node sets, and select textual evidence, interleaving execution with shell search and file inspection. This lets
agents process large node sets in bulk while returning selected text for the model to assess. Execution feedback guides tool creation and revision, while the evolving tools determine what evidence the
agent gathers next. On
benchmark datasets spanning three domains, training-free DKGI exceeds the strongest published baseline by at least 6.7 Hit@1 points on every graph, even with a minimal harness. Controlled ablations show the benefits of multi-turn programming over shell-only access and predefined graph tools, while trajectories show
agents revising code to extend searches or address errors. These findings highlight the value of allowing tool creation and tool use to co-evolve during graph search. Our code and data are available at https://github.com/leopoldwhite/DKGI.
Read the full abstract ▾
Computer Vision
VideoJev: System One Model for Video Understanding and Interaction
Yuhan Zhu, Xiangyu Zeng, Qingyi Si et al. (+15 more)
Visual
agents must turn
video observations into timely decisions to track progress and choose what to do next. Building on the emerging System One paradigm, we introduce VideoJev, a family of models that cast
video understanding and interaction as structured decision tasks. We adapt pretrained
multimodal large
language models (MLLMs) by replacing autoregressive answer decoding with a shared head that scores temporal intervals and textual options against
video evidence. These scores yield event spans or answer choices, unifying temporal grounding and multiple-choice
video question answering. This combines the semantic flexibility of MLLMs with efficient decisions that
agents can use directly. As an interaction unfolds, new goals and intermediate results
prompt further queries about the same visual history. VideoJev therefore reuses visual computation through Cached inference for queries as they arrive and Joint inference for multiple queries in a single forward pass. Across three temporal grounding
benchmarks, VideoJev-4B and VideoJev-35B-A3B improve mean mIoU over their backbones by 6.7 and 10.8 points, respectively, with measured inference speedups of $2.8$-$3.1\times$. On four
video QA
benchmarks, both achieve performance comparable to their backbones in Thinking mode, with measured inference speedups exceeding $100\times$. These results offer a unified, reusable decision interface for composing structured visual judgments into complex, open-ended workflows.
Read the full abstract ▾
All authors Yuhan Zhu, Xiangyu Zeng, Qingyi Si, Chenxu Yang, Yifei Li, Luozheng Qin, Junhao Zhou, Dingyu Yao, Jun Zhang, Chuanyu Qin, Zhiqiu Zhang, Yuandong Yang, Yuqi Xu, Tianyu Zhang, Hongcheng Guo, Jiaqi Wang, Nan Duan, Limin Wang
Artificial Intelligence
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
Ashutosh Hathidara
Controlling an acting LLM
agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human. That decision needs a per-step confidence signal predicting whether the current rollout will eventually succeed. The
agent's own self-reported verbalized confidence is the natural candidate, but existing reinforcement learning methods calibrate it against the correctness of a decision at the current step. We propose a method to calibrate it against the eventual outcome of a multi-step episode: under GRPO, the group of rollouts for a task supplies success labels, and a proper scoring rule scores each step's confidence against the realized outcome. In offline RL on recorded trajectories of a Qwen2.5-7B
agent in ALFWorld, TextWorld, and WebShop environments, the AUROC of step confidence against episode outcome rises from near chance to 0.68-0.85, and the top-10% of steps the
agent is most confident about succeed ~4.3x more often than average. In online RL on the live ALFWorld
agent, four calibration rewards improve early-step AUROC, expected calibration error goes from 0.42 to below 0.12, and selective execution improves over both the untrained
agent and a format-only RL control, without degrading task success. We also introduce an evaluation protocol that separates episode depth, task difficulty, and attempt-level foresight, which shows where the gain lies: the trained
agent recognizes from its first step which tasks it will fail, while telling a succeeding attempt from a failing one at the same task is harder, with some early-window signal emerging on TextWorld.
Read the full abstract ▾
Machine Learning
Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma et al. (+5 more)
Self-
distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or environmental feedback. Recent methods have reported better sample efficiency and generalization than reinforcement learning (RL), but it remains unclear whether these gains extend beyond in-distribution evaluations and whether they stem from privileged
distillation. In this paper, we revisit two representative methods, Self-
Distillation Policy Optimization (SDPO) and On-Policy Self-
Distillation (OPSD), across code, science, tool use, and math
reasoning tasks. We find that their reported gains do not consistently generalize to unseen problems and are largely explained by overfitting or transferring existing
reasoning behavior, rather than effectively using privileged information. Moreover, self-
distillation gradients show weak
alignment with policy gradients that directly optimize expected reward, questioning whether they provide an effective direction for policy improvement. Our experiments across Qwen3 models (1.7B-14B) and OLMo-3-7B suggest that effectively leveraging privileged information to improve
reasoning remains an open challenge. Our code is available at https://github.com/sleepypandu/does-sd-improve-
reasoning
Read the full abstract ▾
All authors Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma, Avinash Balakrishnan, Rameswar Panda, Polina Golland, Yoon Kim, Zhang-Wei Hong
Cryptography and Security
Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
Yang Luo, Tiantian Ji, Zifeng Kang et al. (+4 more)
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution. However, this paradigm introduces a new security risk, which we term Jev Program Decision Hijacking (JPDH): attacker-controlled contexts can redirect program decisions through schema-valid Jev judgments. Existing evaluations focus primarily on model-level attacks or predefined injection channels, leaving attack reachability and downstream security consequences in real-world Jev applications underexplored. In this paper, we present JevProbe, the first automated framework to evaluate JPDH by tracing
adversarial influence from reachable context surfaces through program-consumed decisions to downstream security consequences in real-world Jev applications. Our key insight is that application logic maps diverse Jev judgments to observable decisions, enabling systematic, program-grounded attack evaluation. Across 228 popular real-world Jev applications and 2,273 test cases, 81.5% exhibit decision flips, of which 98.6% lead to potential downstream security impacts. Compared with the strongest adapted baseline, JevProbe improves macro-average Decision Flip Rate (DFR) by 50.4 percentage points, while existing defenses offer limited protection. We further construct JevProbeBench to support systematic evaluation of JPDH in real-world Jev applications. We have responsibly disclosed our findings to Jev application maintainers, pending their responses. The source code of JevProbe and the JevProbeBench
dataset are publicly available on GitHub (https://github.com/xiaoxiaohg8d/JevProbe-).
Read the full abstract ▾
All authors Yang Luo, Tiantian Ji, Zifeng Kang, Yucheng Wang, Yong Liu, Zhiyi Yin, Xinran Liu
Computation and Language
Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning
Huaiwen Pang, Jiale Han, Junying Chen et al. (+2 more)
Legal question answering requires answers that are not only plausible, but also grounded in legally valid and citable evidence. Standard
retrieval-augmented generation often relies on one-shot semantic matching, which is insufficient when legal evidence must be selected according to authority, applicability, and diversity across heterogeneous sources. We introduce Legal-R1, an agentic
retrieval framework for evidence-based legal
reasoning. Legal-R1 decomposes legal
reasoning into a multi-
agent workflow, where a Lawyer
agent learns when to retrieve, which legal source to query, what evidence to seek, and when the collected evidence is sufficient. A Legal Assistant
agent retrieves from normative legal sources and precedent cases with authority-aware and diversity-aware selection, while a Judge
agent generates the final answer from the complete evidence trajectory. We post-train only the Lawyer
agent with masked supervised fine-tuning and trajectory-aware reinforcement learning. Experiments on multiple Chinese legal
benchmarks show that Legal-R1 improves over general-purpose, legal-specific, and
retrieval-augmented baselines.
Read the full abstract ▾
All authors Huaiwen Pang, Jiale Han, Junying Chen, Wenjun Xiao, Benyou Wang
Computation and Language
Jev-ToM: Evaluating Theory of Mind in Typed Decision Models
Kawai Chung, Chunkit Chan, Yuxuan Liu et al. (+9 more)
Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends. Typed decision models offer a potential alternative to generative large
language models for bounded Theory of Mind (ToM) selection. We present Jev-ToM, comparing five typed decision models and seven generative baselines on 11,117 English text questions from nine ToM
benchmarks across six capability groups. TypeSafe Jev reaches 73.2% source-balanced accuracy including native controls and ranks first or second across all six capabilities, leading beliefs, goals/desires/intentions, and emotions. Other typed models show distinct strengths across tasks. Separate resource comparisons suggest that Jev could reduce the cost and waiting time of repeated ToM selection. Confidence-based selection remains
benchmark-dependent, and supplied reasons can repair errors or overturn correct answers depending on their attachment. Candidate expansion reveals distinct selection and output-validity problems. Related-question cues account for most of Jev's downstream gains, with task-dependent effects from predicted states. The findings motivate testing Jev as a ToM selection component in assistants, with task-specific confidence calibration, candidate design, and output validation as integration priorities.
Read the full abstract ▾
All authors Kawai Chung, Chunkit Chan, Yuxuan Liu, Yauwai Yim, Xi Yang, Wenbin Hu, Huihao Jing, Chiu Yeung Tang, Changxuan Fan, Ki Sen Hung, Tsun On Kwok, Haoran Li
Cryptography and Security
DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Chengtao Jian and Kai Yang
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning
vision-
language models (VLMs), yet the security of
multimodal preference data remains largely unexplored. Existing preference poisoning attacks either corrupt explicit supervision signals or require visible triggers, making them detectable under human inspection. We introduce DPOison-VL, the first clean preference poisoning attack against VLM-DPO, which manipulates model
alignment solely through imperceptible perturbations on a small fraction of training images, while leaving all
prompts, responses, and preference annotations semantically intact. We formulate poison construction as a bilevel optimization and derive a gradient
alignment surrogate that efficiently steers image perturbations toward the attacker-specified preference. We further introduce a preference displacement score for principled poison selection with provable first-order optimality under a fixed poison budget, and derive a sufficient condition for preference inversion. Extensive experiments across diverse attack tasks, different VLM architectures and scales, and baseline comparisons demonstrate that DPOison-VL achieves up to 98% ASR with only 2% poisoned data and exhibits cross-model transferability, while largely preserving clean accuracy and general utility. Our findings reveal a critical vulnerability in VLM-DPO, where imperceptible image perturbations in preference training data can silently redirect
alignment.
Read the full abstract ▾
Computer Vision
Recasting DiT for Extreme Image Compression with Hierarchical Visual Priors
Yunuo Chen, Jingnan Gao, Bing He et al. (+6 more)
Pretrained
diffusion models provide powerful generative priors for extreme image compression, but their
stochastic, iterative generation processes are not designed to decode compressed representations directly. We present PrismCodec, which recasts a pretrained
Diffusion Transformer (DiT) as a bitstream-grounded one-step generative decoder. PrismCodec uses the decoded representation in two complementary roles: a projected codec state defines the starting state for generation, while hierarchical visual priors derived from the same decoded latent provide semantic and structural guidance. To bridge the gap between
stochastic, iterative generation and deterministic one-step decoding, we develop a progressive adaptation strategy. We first learn codec-conditioned transport from a noisy neighborhood centered on the codec state, distill it into a one-step mapping, and finally anneal the source perturbation to zero during end-to-end optimization. The resulting decoder reconstructs deterministically from the received representation without additional conditioning bits. Across Kodak, CLIC, and DIV2K, PrismCodec consistently improves rate-perception performance over prior generative codecs, achieving BD-rate reductions of 70-75% in LPIPS and 75-81% in DISTS over StableCodec. Code will be released upon acceptance.
Read the full abstract ▾
All authors Yunuo Chen, Jingnan Gao, Bing He, Jinjing Zhao, Chuqin Zhou, Xiaoyue Ling, Li Song, Guo Lu, Wenjun Zhang
Artificial Intelligence
Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
Haotian Liu, Yingjian Chen, Xiaohang Xu et al. (+4 more)
Large
language models increasingly tackle tasks that require multi-step
reasoning, where errors in intermediate claims can affect the final answer. Self-consistency (SC) improves
reasoning by voting over sampled final answers, but its vote leaves intermediate disagreements unresolved. To address this problem, we introduce DDRG (Disagreement-Driven Verification Guided by
Reasoning Graphs), a framework for selective correction from a frozen bank of
reasoning traces. Our insight is that graph
alignment can expose claim-level disagreements and provide correction evidence without expanding the sampled trace bank. DDRG builds source-grounded claim graphs and sends localized conflicts to an answer-blind verifier. A verifier-supported refutation that reaches the majority answer's supporting path triggers one focused repair; otherwise, DDRG returns the exact SC vote. Experimental results across five
benchmarks show that native zero-shot DDRG improves macro-average accuracy over direct answering by 8.65 and 15.83 percentage points for Qwen2.5-7B and Llama3.1-8B. It also exceeds CoT, the evaluated GoT and GoV question-answering adaptations, and SC on this macro metric. DDRG links local verification to selective correction without enlarging the initial candidate bank.
Read the full abstract ▾
All authors Haotian Liu, Yingjian Chen, Xiaohang Xu, Lang Huang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
Computation and Language
From Hindsight to Foresight: Dissecting Clinical Evidence Acquisition in Large Language Models
Ziyang Ling
Large
language models (LLMs) often diagnose full sight, static clinical cases well yet struggle in foresight, dynamic diagnosis. Prior work has improved this limitation by quantifying the information models acquire and by developing stronger follow-up strategies to improve diagnostic accuracy. In contrast, we introduce a distinctive hindsight to systematically dissect why LLMs fail to acquire diagnostically critical evidence, tracing the failure from evidence identification, utilization and downstream diagnostic updating through not only diagnostic accuracy, but also evidence coverage, trajectory dynamics, and elicited probability and information
entropy. Starting experiments from the breakdown at the level of capabilities, to the diagnosis of the pre-event state before the evidence arrives, and to the post-event state transition after the evidence arrives, our research has revealed the profound limitations and internal causes existing in the dynamic diagnostic process. At the same time, we have also conducted sufficient verification and generalization experiments to prove that these limitations are widespread. Together, these findings shift the central challenge from whether LLMs possess relevant clinical knowledge to whether they can identify, acquire, and effectively use the right evidence under clinical diagnosis and conduct a more detailed mechanism analysis to identify the exact location of the capability gap.
Read the full abstract ▾
Computer Vision
LLM2R: From Large Language Models to 3D Reassemblers
Zhouhan Zhong, Qiuhong Shen, Xingyi Yang et al. (+2 more)
3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a part is rarely determined by its own geometry, the task demands
reasoning over the entire part set, and existing methods, which rely on pairwise relations or iterative generation and verification, scale poorly to objects with many parts. We present LLM2R, which casts part assembly as sequence modeling with a pretrained decoder-only large
language model (LLM): a Point-BERT encoder and a Q-Former compress each part into a block of
geometric tokens, the blocks of all parts are concatenated, and a causal LLM adapted with Low-Rank Adaptation (LoRA) processes the sequence in one forward pass. Causal
attention, however, lets the hidden states of a part observe only the parts that precede it. LLM2R therefore appends a block of learnable summary
tokens after the last part: these
tokens follow every part, so their states aggregate the whole assembly at a constant
token cost, and a part-aware pose head fuses each part's states with them before predicting its rotation and translation. One architecture thus handles semantic and
geometric assembly and predicts all poses in a single non-autoregressive pass. LLM2R achieves the highest part accuracy and success rate on all three PartNet categories, the best rotation error, translation error, and part accuracy on PartNeXt, and the lowest translation error and fastest inference on Breaking Bad, where only a fracture-specialized method is more accurate. Its advantage grows with the number of parts: at 100 parts it exceeds GARF by 33.5 points in part accuracy on Breaking Bad and Assembler by 29.1 points on PartNet, and it transfers zero-shot to unseen categories with more than 16 points higher part accuracy than the strongest of three baselines.
Read the full abstract ▾
All authors Zhouhan Zhong, Qiuhong Shen, Xingyi Yang, Jinyi Xu, Xinchao Wang
Artificial Intelligence
AgentStripes: An Evidence-Graded Maturity Model for AI Agents
Nutan Kumar Naik, Vijay Prasad Poudel, Aditya Kumar Saroj et al. (+2 more)
Benchmarks report what an Artificial Intelligence (AI)
agent can do on a task suite, but not whether one released version has been engineered with the controls that make it reliable, safe and observable, or how strongly that is shown. This paper proposes AgentStripes, an evidence-graded maturity model for AI
agents. It defines levels (0 to 7 stripes), process areas (12 areas holding 40 capabilities), three gates (basic, safety, proof) that hold an
agent at a level however high its score, and evidence grades E0 to E5. Each applicable capability receives a rating from 0 to 3 and a separate evidence level; these are combined into a credit, aggregated into a severity-weighted score and converted into stripes that the gates limit. Instruments gather evidence,
language-model judges interpret it under explicit criteria, and the arithmetic is deterministic. The model is compared with standards at topic level without a claim of conformance, and an unexecuted validation protocol is specified. An empirical evaluation (exploratory, non-confirmatory) of 30 public Python
agent repositories, with static evidence only, is a demonstration and not a validation: static evidence caps every final stripe at 2, 26 repositories end at one stripe and 4 at two, and this distinction is unreliable, since re-judging changed the final stripe of 4 of 22 repositories (engine, dossier and panel changed), whereas none of 8 panel-only repeats, all at stripe 1, changed. The parameters are expert conventions without outcome based calibration, and the stripes have not been shown to predict reliability or safety.
Read the full abstract ▾
All authors Nutan Kumar Naik, Vijay Prasad Poudel, Aditya Kumar Saroj, Saurav Samantray, Abhishek Patel
Artificial Intelligence
Rongtian Ye
Point-in-time (PIT)
agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access predicts evidence gathering in 48 historical company-comparison tasks. Independent closed-book revenue probes identify the better-remembered company for each model on tasks with unequal recall, fixing the predicted direction before
agent runs. We then compare paired runs with real or anonymized company identities while keeping external evidence PIT-valid. Both Qwen and DeepSeek recalled future facts, but neither supported the prespecified shift toward the better-remembered company. Qwen's four allocation estimates on 28 unequal-recall tasks were negative, with descriptive intervals spanning zero. A prospective DeepSeek replication showed an inverse pattern across all four metrics on 20 such tasks, with intervals below zero. These estimates remained negative after each company, pair, and future-fact omission, and all four post-hoc max-T-adjusted sign-flip p-values were below .05. In a prospectively specified follow-up, explicit future facts produced small estimated shifts away from the supplied-fact company, with intervals spanning zero, while final choices shifted toward it. The mechanism behind the natural inverse pattern remains unresolved. These findings support separate assessments of
memory accessibility, search allocation, and final outputs alongside cutoff checks on external evidence.
Read the full abstract ▾
Computer Vision
Rethinking Projector Training in Multimodal LLMs
Fabian Gröger, Naël Ouerghemi, Shuo Wen et al. (+1 more)
Multimodal LLMs are typically trained by first aligning a
vision encoder with a
language model via projector training on large image-caption
datasets, followed by joint training of the full
multimodal model. Despite its widespread use, the role of the projector training stage remains poorly understood. We find that (i) using only $10$ to $20\%$ of the data for training the projector already recovers most downstream performance gains, and (ii) projectors trained on different
datasets can be linearly interpolated while largely preserving performance. These results suggest that projector training mainly performs a coarse
alignment, which many different projectors achieve equally well. Motivated by these findings, we propose PORTAL, a training-free projector initialization that requires neither paired image-caption data nor gradient-based optimization, but only per-modality summary statistics. PORTAL computes an optimal-transport-based map between Gaussian approximations of the
vision and
language feature distributions on a shared principal subspace, so that the projector training stage can be skipped entirely. Without any paired data, PORTAL matches the standard pipeline trained on 558k image-caption pairs across six LLM backbones, two
vision encoders, and 16
benchmarks. It outperforms that pipeline in $3$ of $7$ (
vision encoder, LLM) settings and reaches an average $98\%$ of its score across the other four.
Read the full abstract ▾
All authors Fabian Gröger, Naël Ouerghemi, Shuo Wen, Maria Brbić
Sound
PhysicsSliders: Learning Physical Controls for Audio Foley Generation
Peiwei Chang, Yongqiang Chen, Yuelan Cheng et al. (+6 more)
Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictably to these controls, both individually and in combination. We present \method\ (PXS), trained on simulated contact sounds with 15 material, geometry and contact parameters. Two separately trained variants accept direct parameter inputs or numerical captions. PXS controls hardness, size, speed and damping, supports room descriptions and produces spectrally distinct outputs at fixed targets. When controlling damping and size together, specifying thickness improves frequency accuracy and joint target delivery. Measurements from real recordings define effective-damping targets, which simulator inversion maps to generation inputs without real-audio fine-tuning. Across 18 impact classes from five real-audio
datasets, PXS-Physical follows these targets with mean grouped Spearman correlation $\rho=0.976$ and class-median error 0.094 dex (a factor of 1.24).
Read the full abstract ▾
All authors Peiwei Chang, Yongqiang Chen, Yuelan Cheng, Liting Gao, Yishun Lu, Li Zhang, Mark D. Plumbley, Philip J.B. Jackson, Wenwu Wang
Robotics
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
Changyeon Kim, Kimin Lee, Yashraj Narang et al. (+1 more)
Reinforcement learning (RL) post-training improves
robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more: learning new tasks efficiently while retaining previously acquired behaviors. Existing continual RL methods on top of VLAs mitigate forgetting but rely on on-policy updates with limited forward transfer, whereas off-policy methods improve single-task sample efficiency without addressing learner persistence across tasks. We propose ACCRUE, a continual off-policy RL framework that carries lightweight actor and critic networks across tasks, allowing each stage to reuse behavioral and value knowledge acquired through prior RL. The inherited critic adapts only on current-task transitions and guides current-task actor learning, while prior behavior is preserved by distilling the actor toward cached targets on a small number of retained episodes. Fixed visual features keep the inherited learner and its replay compatible with base-policy updates. Across contact-rich assembly sequences in simulation and on real-
robot hardware, ACCRUE accelerates subsequent-task learning with near-zero forgetting and significantly reduces real-
robot training time by 31.0% to 68.5%.
Read the full abstract ▾
All authors Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
Cryptography and Security
Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence
Tobias Hürten, Johannes F. Loevenich, Florian Spelter et al. (+5 more)
This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emulation, realistic user behaviour modelling for benign network traffic and
adversarial profiles, and the generation of cybersecurity scenarios through open toolkits. By supporting live and deferred feature extraction at the packet and flow levels, the gym facilitates the creation of labelled synthetic
datasets for training Deep Neural Network (DNN)-based Intrusion Detection Systems (IDSs), as well as developing and evaluating modular components for autonomous defence
agents through emulated interactions. While evaluation of a DNN classifier within the gym shows high in-domain performance, achieving near-perfect recall on
adversarial network flows, our experiments reveal a significant sensitivity to domain shift, showing that even minor changes in network composition, such as variations in traffic protocol distribution, can lead to a catastrophic collapse in model transferability and detection performance.
Read the full abstract ▾
All authors Tobias Hürten, Johannes F. Loevenich, Florian Spelter, Erik Adler, Laurin Holz, Maxime Schwarzer, Thies Moehlenhof, Roberto Rigolin F. Lopes
Machine Learning
Fairness under Prediction Error in Predict-then-Optimize Pipelines
Hilda Adwubi Osei
Fairness constraints in predict-then-optimize pipelines are necessarily enforced on predicted outcomes $\hat{y}$, since true outcomes $y$ are unobserved at decision time. We study whether a demographic parity constraint enforced this way continues to hold against $y$, and how the resulting violation scales with prediction error. Using a budget-constrained allocation problem solved as a linear program, we show empirically that the true-outcome
fairness gap grows with prediction error $\sigma$ and saturates, well fit by $c(1 - e^{-\sigma/\tau})$ with $c = 0.1545 \pm 0.0103$ and $\tau = 3.9045 \pm 0.3745$; its mean is invariant to sample size while its variance decays at the standard $O(1/\sqrt{n})$ rate. We derive a two-part theoretical bound: a closed-form local sensitivity result showing the gap's first-order response to prediction error depends on only two individuals per group, validated against the solver to within three significant figures; and a universal, error-independent ceiling following from the boundedness of the decision variable, confirmed consistent with but looser than the empirical saturation level. On US Census income data, enforcing demographic parity on a trained predictor's output reduces an unconstrained disparity in true income to roughly one-third of its original size, leaving 34.4% $\pm$ 3.3% (California) and 35.7% $\pm$ 1.8% (Texas) of the disparity intact and undetectable from the predictions alone – consistent not only in mechanism but in approximate magnitude across two states with different demographics and income distributions, and stable across ten independent train/test splits in each. A
fairness constraint that appears fully satisfied at decision time can mask a substantial, systematic violation of the outcome it was meant to protect.
Read the full abstract ▾
Computational Complexity · Cross-listed from quant-ph
$T$-efficient unitary synthesis via block-sparse Hamiltonian simulation
Diyi Liu, Shuchen Zhu, Wibe Albert de Jong et al. (+3 more)
We construct Clifford+$T$
circuits implementing arbitrary $n$-
qubit unitaries with worst-case $T$-count $\widetilde{O}(N^{8/7})$ at constant operator-norm error, where $N=2^n$, improving the previous exponent $5/4$. The construction uses $\widetilde{O}(N^{6/7})$ clean ancillas. The main idea is to reduce the data addressed by each query to the block-encoding
circuit for a sparse piece while controlling the additional simulation work needed to combine the pieces. We simulate a Hermitian logarithm of the target by flattening its traceless part with a two-layer random similarity transformation, randomly partitioning the transformed generator into block-sparse Hermitian pieces, and combining their evolutions using qDRIFT. For a target operator-norm error $\epsilon\in(0,1/2)$, let $L=\log_2(N/\epsilon)$, the
qubit count plus the requested bits of accuracy. By successively correcting the approximation error, we obtain a
circuit using $\widetilde{O}(N^{8/7}L^{3/7}+NL)$ $T$ gates and $\widetilde{O}(N)$ clean ancillas whenever $L\le N$. We also prove that, at constant precision, the exponent $8/7$ is optimal within a sequential block-SELECT model.
Read the full abstract ▾
All authors Diyi Liu, Shuchen Zhu, Wibe Albert de Jong, Di Fang, David Williams-Young, Chao Yang
Computation and Language
Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages
Irem Ecem Yelkanat, Faeze Ghorbanpour and Alexander Fraser
Annotator disagreement is increasingly recognized as a meaningful property of subjective tasks, rather than merely noise to be removed. Predicting which items are likely to be contested could help allocate annotation effort and route difficult cases to human review. We propose predicting disagreement from interpretable semantic properties of the text. An LLM answers a set of binary questions covering harmful-content characteristics, disagreement-related cues such as borderline severity and missing context, and
language-sensitive cues such as local slurs. A classifier predicts disagreement from these answers, and we analyze which questions contribute most to the predictions. Across four
datasets in English, German, and Turkish and three open-weight LLMs, our structured question features outperform direct prompting by 10.5 ROC-AUC points and the strongest text-based baselines by 5.0 points. A compact subset of eight questions performs within 1.5 ROC-AUC points of the full twenty-question set. In leave-one-
dataset-out evaluation, models retain roughly 90-95% of their in-domain ROC-AUC. Across models and
datasets, questions about derogation, missing context, and decision boundaries serve as the strongest predictors, suggesting that what makes harmful content contested is partly observable in the text.
Read the full abstract ▾
Sound
GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition
Ting Zhu, Huizhi Liang, Boguslaw Obara et al. (+2 more)
Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as
speech and text. Psychological studies suggest that emotions exhibit latent hierarchical structured relationships in their semantic representations. However, most MER approaches rely on Euclidean representations, which capture fine-grained cross-modal interactions but do not explicitly provide a
geometric prior for organizing hierarchical emotional structures. To mitigate this gap, we propose GeoMER, a joint Euclidean-
Hyperbolic modeling framework that introduces
hyperbolic emotion-core routing to capture higher-level, abstract emotional representations for MER. The proposed framework jointly models
token-level cross-modal semantic interactions and latent emotion representations in two complementary
geometric spaces. Specifically, GeoMER consists of a Euclidean
Multimodal Fusion Module (EuclFusion) for
multimodal representation fusion and a
Hyperbolic Geometric Core Routing (HypGeoRoute) module that performs geometry-aware core assignment and aggregation in a
hyperbolic manifold to capture more abstract feature representations. The HypGeoRoute module complements the Euclidean
token-level modeling. We experiment on the IEMOCAP
multimodal MER
benchmark and demonstrate that the proposed method achieves the best performance, with 83.54% weighted accuracy and 83.35% unweighted accuracy, outperforming Euclidean baselines, including MemoCMT.
Read the full abstract ▾
All authors Ting Zhu, Huizhi Liang, Boguslaw Obara, Shufei Duan, Varun Ojha
Cryptography and Security
X.js: A Live Benchmark for Node.js Taint-Style Vulnerabilities
José Afonso, João Madeira Pereira, Ronghao Ni et al. (+3 more)
JavaScript vulnerabilities in npm packages pose a significant risk to the Node$.$js ecosystem, and a growing body of work aims to detect, exploit, and mitigate them. Studying and evaluating this work requires up-to-date collections of real vulnerabilities, yet the most commonly used
datasets stop recording vulnerabilities in 2022. We present X$.$js, a live
benchmark of real-world Node$.$js taint-style vulnerabilities covering code and command injection, prototype pollution, and path traversal. Built from 1,738 advisories collected through mid-2026, primarily from the GitHub Advisory Database, X$.$js pairs each vulnerability with precise source and sink locations, a validated executable exploit and its execution trace, and, when available, a patched version of the package. X$.$js supports long-term reproducibility and growth: dependencies are mirrored in a self-hosted registry to guard against package removal from the ecosystem, and dedicated infrastructure generates and validates exploits for newly reported vulnerabilities. The current release contains 1,159 validated exploits for 965 packages. Using X$.$js, we characterize how the frequency, structure, and complexity of Node$.$js taint-style vulnerabilities have evolved over time. We find that these vulnerabilities are increasingly reported in large packages: the median vulnerable package grew from roughly 250 LoC in 2021–2022 to 6,100 LoC in 2026.
Read the full abstract ▾
All authors José Afonso, João Madeira Pereira, Ronghao Ni, Limin Jia, José Fragoso Santos, Pedro Adão
Artificial Intelligence
Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling
Cong Hua, Qianqian Xu, Zitai Wang et al. (+4 more)
Sampling-based test-time scaling enhances LLM
reasoning by aggregating multiple
reasoning paths for the same query. Existing methods use answer frequencies or path confidence to compute candidate scores, which do not explicitly characterize comparisons between competing answers. Inspired by the Condorcet principle in social choice theory, we introduce pairwise confidence comparisons between paths supporting different answers to capture answer-level comparative advantage. We combine this comparative evidence with voting support through a KL-regularized objective. Theoretically, we show that this comparative-advantage is equivalent to the adjustment to the traditional voting logits. In this way, our proposed Pairwise-Guided Logit Adjustment (PGLA) framework allows comparative evidence to compensate for weaker voting support and correct voting-based ranking errors. Experiments on 10 challenging
benchmarks including mathematical
reasoning, knowledge
reasoning, and code generation with 7 models ranging from 1.7B to 32B parameters speak to the effectiveness of this plug-and-play term. Additional evaluations with external reward scores and online sampling further demonstrate its applicability.
Read the full abstract ▾
All authors Cong Hua, Qianqian Xu, Zitai Wang, Zhiyong Yang, Shilong Bao, Linchao Zhang, Qingming Huang
Numerical Analysis
A two-level preconditioner for discontinuous virtual element methods with irregular subdomains
Juan G. Calvo and César Herrera
We introduce and analyze a two-level overlapping additive Schwarz preconditioner for discontinuous Galerkin discretizations of virtual element spaces on general polygonal meshes in two dimensions, for a second-order elliptic problem whose coefficient is constant on each subdomain and may have large jumps across the interface. The discretization is a weighted symmetric interior penalty formulation: the averages carry the coefficient and the penalty is scaled by its harmonic mean across each edge, which keeps the method consistent and makes the constants of the analysis independent of the coefficient. The coarse space is obtained from a virtual, continuous partition of unity with a single degree of freedom per subdomain vertex, and is therefore applicable to the irregular subdomains produced by a graph partitioner; the discrete harmonic extension used to build it may be replaced by a cheaper projection onto
polynomials of low degree. We prove that the condition number of the preconditioned system is bounded by $C(1+\log(H/h))(1+H/\delta)$, where $H$, $h$ and $\delta$ denote the subdomain diameter, the mesh size and the overlap, and where $C$ is independent of the number of subdomains and of the contrast of the coefficient, provided the latter is quasi-monotone. This is the same bound known for the conforming case and the analysis allows for hanging nodes. We also show, by an explicit example, that the quasi-monotonicity assumption cannot be dispensed with. Numerical experiments with structured triangular, hexagonal and Voronoi meshes, and with subdomains obtained both by uniform partitioning and by METIS, confirm the theory.
Read the full abstract ▾
Artificial Intelligence
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops
Yubo Li, Ramayya Krishnan and Rema Padman
System One models choose an
agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is nothing to inspect: did the model misread what the
agent has seen, or read it correctly and still act wrongly? We answer behaviorally. On a frozen
benchmark of
agent decision states from simulated environments, customer-service policies, tool use, web navigation and coding, we pair every next-action question with factual probes about the same state, each answered independently. Across seventeen fast systems and a
reasoning model, the answer is consistent: most wrong actions follow correct reading, and the more accurate a system, the more of its errors take this form. These errors are not noise; they gather on the same states across systems of every kind. Where the probed facts provably determine the action, models that read every fact still fail to combine them, and their own answers, composed by code, repair the failure. On real states, what is missing is often not a fact but the next sub-goal.
Read the full abstract ▾
Information Theory
Rate-Splitting Multiple Access for RIS-Enabled Full-Duplex Communications with User Relaying
Yuwen Cao, Hui Wang, Tomoaki Ohtsuki et al. (+1 more)
Rate splitting multiple access (RSMA) has emerged as a promising non-orthogonal transmission mechanism to improve spectral- and energy efficiency, and user
fairness in multi-
antenna broadband channels. To further enhance its performance, in this paper we investigate a novel cooperative RSMA (C-RSMA) transmission framework assisted by reconfigurable intelligent surface (RIS) and user relaying. More specifically, we first formulate the common- and private-rate maximization problem satisfying the transmit power constraint, by jointly optimizing the transmit beamformers at the BS and the reflective beamformer at the RIS. The above formulated problem is an intractable and NP-hard problem as the optimization variables are coupled and the strong residual self-interference (SI) is involved. To conquer the challenge mentioned above, we propose a low-complexity alternative optimization approach to jointly optimize the transmit and reflective beamforming. Simulation results show that our approach is capable of enabling superior sum-rate performance than the RIS-assisted space division multiple access (SDMA), half-duplex RSMA, and SDMA without using RIS schemes.
Read the full abstract ▾
All authors Yuwen Cao, Hui Wang, Tomoaki Ohtsuki, Shahid Mumtaz
Machine Learning
When More Objectives Make Identification Easier: The Role of Preferences and Feedback
Bo Xue, Ji Cheng, Yuanyu Wan et al. (+1 more)
Best-arm identification (BAI) aims to identify the optimal arm using as few samples as possible. While most existing work focuses on a single objective, many real-world applications involve multiple criteria, which motivates the study of BAI in multi-objective bandits. Intuitively, multi-objective identification seems harder, since the learner must identify optimal arms in a higher-dimensional reward space; however, the additional objectives also provide richer feedback that can reduce the required exploration. In this paper, we characterize when and why multiple objectives can make BAI easier. For Gaussian bandits, we establish a characteristic-time lower bound for fixed-confidence identification that holds uniformly across preference orders. Through explicit comparisons under Pareto, linear, and lexicographic preferences, we reveal three phenomena: (i) identifying a larger optimal set can require fewer samples than identifying a unique optimum; (ii) the advantage of vector feedback over coordinate feedback depends fundamentally on the preference order; and (iii) multi-objective identification can require fewer samples than even the easiest corresponding single-objective problem. Finally, we propose Order-Aware Track-and-Stop (OATS), an
algorithm that is correct at any prescribed confidence level and asymptotically matches the lower bound.
Read the full abstract ▾
All authors Bo Xue, Ji Cheng, Yuanyu Wan, Shuang Qiu