Machine Learning
When Less Data Favors Smaller Teachers: Rethinking Teacher Capacity and Data Selection for Knowledge Distillation
Minjae Park, Taesun Yeom and Jaeho Lee
Data
pruning reduces the training cost of knowledge
distillation (KD). However, the preferred teacher capacity changes with the data budget: smaller teachers can outperform larger ones when limited training data are available. Understanding what drives this shift is important not only for teacher choice but also for identifying which samples are useful for
distillation. We analyze teacher supervision by decomposing it into relational ordering—the ranking of classes—and score geometry—the magnitudes and margins of class probabilities—and show that the small-teacher advantage in the low-data regime arises not only from score geometry but also from relational ordering. Beyond understanding teacher capacity, our analysis reveals two properties of effective subsets: samples should match the difficulty appropriate for the available budget, and their relational signals should be diverse rather than redundant. Based on these findings, we propose DVA (Difficulty- and Volume-Aware data selection for KD), a training-dynamics-free method, which uses a small teacher as a proxy for budget-aware difficulty filtering and class-conditional relational volume maximization. Despite requiring no training dynamics statistics, our method remains competitive with training-dynamics-based methods while consistently outperforming training-dynamics-free baselines.
Read the full abstract ▾
Machine Learning
FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL
Xun Wang, Ruishuo Chen, Yu Chen et al. (+2 more)
Looped architectures scale computation by reusing the same parameters across recurrent steps, and recent work shows that they substantially improve deep reinforcement learning policies on long-horizon tasks. Since recurrent depth directly controls computation, one may expect looped policies to naturally support elastic inference across recurrent depths. Surprisingly, we find that pretrained looped policies exhibit severe recurrent-depth specialization: reliable decisions are concentrated near the full trained depth, tying deployment computation to this depth even when less computation may suffice. Achieving depth elasticity, i.e., reliable decisions across recurrent depths with adaptive computation at deployment, therefore remains a key challenge. To address this, we propose FlexLoop, a novel post-training framework that converts pretrained fixed-depth looped policies into depth-elastic policies. FlexLoop keeps training on the original RL objective to preserve full-depth capability while performing adjacent-depth policy
distillation to progressively transfer decision quality from deeper to shallower recurrent steps. The resulting policy supports reliable inference across recurrent depths and enables state-wise adaptive inference through recurrent-depth consistency. Experiments on $30$ online and offline long-horizon goal-conditioned environments show that FlexLoop preserves full-depth performance while making shallower depths effective. Keeping competitive performance, FlexLoop reduces average recurrent depth by up to $\bf{43\%}$ and achieves up to $\bf{1.34\times}$ wall-clock speedup in a stress test.
Read the full abstract ▾
All authors Xun Wang, Ruishuo Chen, Yu Chen, Zhuoran Li, Longbo Huang
Computer Vision
PACER: Progressive Availability-Conditioned Evidence Routing for Radiology Report Generation under Incomplete Clinical Context
Yulong Chen, Yadong Liu, Haoyu Cao et al. (+3 more)
Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose availability varies across examinations. However, accommodating different input combinations does not ensure effective evidence use: generated reports may still omit or inaccurately describe clinically relevant findings. To address this problem, we propose PACER, a Progressive Availability-Conditioned Evidence Routing framework for structured incomplete-context RRG that follows a Refine-Calibrate-Commit pipeline. It first refines observed visual representations through endpoint-preserving patchwise routing across frozen encoder depths, incorporating complementary cues while retaining the pretrained terminal representation. It then calibrates the
language-model prefix according to the observed evidence and availability state, adapting the shared generator's conditioning as the available source set changes. Finally, it generates polarity-structured clinical commitments before the report in the same autoregressive trajectory, providing structured clinical context for subsequent generation. Experiments demonstrate state-of-the-art clinical efficacy across all four MIMIC-RG4 settings and strong MIMIC-CXR performance, while maintaining competitive
language-generation quality.
Read the full abstract ▾
All authors Yulong Chen, Yadong Liu, Haoyu Cao, Sen Xu, Yueying Wang, Jie Wen
Robotics
Model-Informed Safe Reinforcement Learning for Bipedal Locomotion via Step-to-Step Prediction
Victor Paredes and Ayonga Hereid
Humanoid robots promise versatile mobility in cluttered, human-centric environments, but real deployment demands principled safety. Classical model-based gait generators yield interpretable motions but often lack the robustness and adaptability of modern reinforcement learning (RL) based approaches. We propose a model-informed reinforcement learning framework anchored to the analytical Angular Momentum Linear Inverted Pendulum (ALIP) template. We provide a step-to-step safety certificate for ALIP stepping via a discrete exponential control barrier function (DECBF) and use it as (i) a training-time shaping signal and (ii) a runtime action filter that minimally adjusts swing-foot placement to satisfy template-level constraints. Full-order safety is evaluated empirically on the Digit
humanoid in MuJoCo with a whole-body controller stack. Compared to an unconstrained baseline, our approach reduces safety-violation events in the reported external-disturbance trial, while larger lateral-velocity transients reveal a safety-tracking tradeoff.
Read the full abstract ▾
Robotics
Trajectory-Safe Orienteering for Human-Robot Shared Environments
Songqun Gao, Elena Basei, Marco Roveri et al. (+2 more)
Orienteering problem (OP) has wide real-world applications and also great potential in human-
robot collaboration. However, existing approaches struggle to simultaneously ensure safe and feasible trajectories while achieving high-quality task execution in shared workspaces. To this end, this work studies the OP with time windows and variable profits (OPTWVP). A two-stage DEcoupled discrete-Continuous Optimization with Service-time-guided Trajectory (DeCoST) approach is proposed to effectively solve OPTWVP in shared spaces. Meanwhile, the safety-aware time windows of nodes and the discretized workspace are introduced to ensure collision-free trajectories between the end effector and the human. Preliminary results validate the effectiveness of DeCoST in generating collision-free trajectory plans while preserving the quality of orienteering tasks.
Read the full abstract ▾
All authors Songqun Gao, Elena Basei, Marco Roveri, Luigi Palopoli, Daniele Fontanelli
Robotics
ARS: Agentic Reward System for Robot Learning
Sheng Hu, Weiyi Lu, Lingbing Zeng et al. (+5 more)
Progress reward modeling is the problem of estimating how a
robot's behavior changes task progress over time. Reliable estimation requires distinguishing meaningful state changes from failed attempts and task-irrelevant actions. We introduce the Agentic Reward System (ARS), an inference framework for progress reward modeling with general-purpose
vision-
language models (VLMs), without additional reward-model training. Given an offline trajectory and a task instruction, ARS uses adaptive visual inspection for both event proposal and verification. A subagent proposes a task-relevant event timeline, which a primary
agent verifies and revises before estimating per-frame progress. ARS can incorporate optional terminal outcome labels and visual references to inform its judgments. It can also audit progress estimates from external reward models. We evaluate ARS with a 27B VLM on a controlled semantic-mismatch
benchmark and downstream policy learning in simulation and on a real
robot. The
benchmark reveals that several evaluated reward baselines assign spurious progress to wrong-object manipulation even in simple pick-and-place scenes. ARS better suppresses these errors and outperforms these baselines in simulation policy learning. We further demonstrate that ARS supports long-horizon policy learning from mixed-quality offline experience on real-
robot multi-screw fastening in a full-scale laboratory replica of an industrial washing-machine assembly line. These results suggest that structured inference and verification can improve the usefulness of general-purpose VLMs for
robot reward modeling. Code is at https://github.com/midea-ai/ars
Read the full abstract ▾
All authors Sheng Hu, Weiyi Lu, Lingbing Zeng, Gan Weng, Weiwei Zhang, Kai Xie, Xiaofeng Mou, Yi Xu
Networking
Deconstructing BLE Multi-hop: a Model-based Approach to Quantifying the Challenges
Bozheng Pang, José Alamos, Thomas C. Schmidt et al. (+1 more)
Bluetooth Low Energy (BLE) was originally designed for point-to-point communication, but BLE multi-hop networks have attracted academic and industrial interest. Multi-hop communication, however, introduces desynchronized nodes to the network due to the difference in individual clocks. In this paper, we study the impact of clock drift on a BLE multi-hop network. The aim is to find out if a BLE multi-hop network can be properly set up, why, and how. For this goal, we develop a mathematical model to quantify the collision probability among BLE connections managed by a single device. We provide a simplified version of the model for constrained deployment. The impact of clock drift and our mathematical model are validated through practical experiments. Afterward, we find that a BLE multi-hop network cannot eliminate the impact of clock drift in most cases. Moreover, from a long-term point of view, the collision between BLE connections occurs with a fixed frequency. We further analyze the limitation of using BLE to form multi-hop networks, and propose possible solutions, such as
topology limitation, changes to BLE stack or hardware. This paper is a clear and quantitative problem statement on the limitations of using BLE in multi-hop networks.
Read the full abstract ▾
All authors Bozheng Pang, José Alamos, Thomas C. Schmidt, Matthias Wählisch
Computation and Language
CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR
Bashar Talafha, Samar M. Magdy, Aisha Alansari et al. (+36 more)
We present Cardamom, a micro-dialectal Arabic
speech dataset designed to support fine-grained evaluation and adaptation of automatic
speech recognition (ASR) systems. Community-curated by native speakers familiar with the represented varieties, Cardamom contains approximately 40 hours of transcribed YouTube
speech spanning 21 micro-dialects across Egypt, Jordan, Lebanon, Mauritania, Palestine, and Saudi Arabia. Each segment is annotated with one or more operational micro-dialect labels, code-switching information, and utterance-level perceived gender, enabling analysis of sub-country variation that is obscured by conventional country-level labels. We describe the collection and annotation process, motivate the micro-dialect inventory linguistically, and
benchmark four
multilingual ASR systems in zero-shot and adapted settings. The strongest zero-shot system obtains 43.47% aggregate WER, with particularly high error rates on Mauritanian and Lebanese varieties; adaptation on Cardamom reduces its WER to 35.21%. Audio-based identification experiments further highlight the difficulty of fine-grained micro-dialect recognition: across three training seeds, a dedicated classifier obtains 46.85% accuracy and 31.95% F1. Cardamom provides a resource for studying localized dialectal variation and developing Arabic
speech systems with broader regional coverage.
Read the full abstract ▾
All authors Bashar Talafha, Samar M. Magdy, Aisha Alansari, Alaa Alkhawaldeh, Abdurrahman Juma, Sharaf Makahleh, Nour Gamal, Omar Attia, Hanaa Kurdi, Najwa Rizk, Maysa Anaya, Hessah Altimyat, Layal Alhazmi, Shumukh Alotaibi, Hajar Alhadaris, Rayan Alomari, Rahaf Almalaq, Malak Alkhorasani, Sara alghamdi, Rahaf Alshamrani, Nsrin Ashraf, Ibrahim Jaradat, Nada Qardahji, Yasmin Zaraket, Elmoukhtar Brahim, Sidi Ebeidy, Oumoulmouminin Mahmoud, Yahjeb Bouha Khatraty, Meya Haroune, Mohammad Ghaddar, Mohamad Eldirany, Rashed Alamoush, Tala Chhaytle, Nuha Albadi, Yahya El Hadj, Hamzah Luqman, Fadi A. Zaraket, Mustafa Jarrar, Muhammad Abdul-Mageed
Computer Vision
When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes
Sungguk Cha, Mintae Kim, Youngsub Han et al. (+2 more)
Reliable visual question answering requires correct answers when evidence is sufficient and abstention when it is not. We introduce a
benchmark that connects complete-question evaluation with explicit evidence for its labels across PlotQA charts, CLEVR rendered scenes, and GQA photographs. Each question groups original and edited images, presented independently; success requires every supported answer and every required abstention to be correct. For chart missing-information labels, executable witnesses establish that admissible complete charts give different answers but identical pixels after masking. Scene labels follow source programs and edits, with a residual-cue analysis for photographs. Across 72,000 responses from six model configurations, the highest observed complete task success rates are 57.0%, 43.5%, and 33.7%, respectively. On charts, the strongest configuration achieves 96.2% per-view decision accuracy, yet 265 of its 835 groups with every decision correct still contain incorrect answers. Evaluating supported answers and necessary abstentions together exposes failures that answerability decisions alone conceal.
Read the full abstract ▾
All authors Sungguk Cha, Mintae Kim, Youngsub Han, Byoung-Ki Jeon, Sangyeob Lee
Computer Vision
SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
Hangyul Yoon, Hyungyung Lee, Edward Choi et al. (+1 more)
Vision-
language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods often remain dependent on task-specific finetuning because radiology reports are lengthy, clinically dense, and difficult to align with simple zero-shot
prompts. Recent sentence-level approaches partially address this limitation using clinical phrases extracted by large
language models (LLMs), but they largely overlook the intrinsic characteristics of radiology discourse. In particular, limited positive-pair diversity constrains further gains, while clinically equivalent sentences frequently recur across patients, creating false negatives in contrastive learning. To address these issues, we propose SentZero, an enhanced sentence-centric VL pretraining framework for zero-shot, multi-task CXR analysis. SentZero introduces LLM-based abstract-level sentence structuring and mapping to expand positive-pair diversity, together with an additional loss term to mitigate false negatives. We further introduce sentence-conditioned residual modulation of visual
embeddings, enabling visual features to adapt to the semantic characteristics of each input sentence. Across diverse downstream tasks and
datasets, SentZero improves zero-shot generalization and outperforms prior multi-task zero-shot methods.
Read the full abstract ▾
All authors Hangyul Yoon, Hyungyung Lee, Edward Choi, Eunho Yang
Machine Learning
Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases
Jiangtao Lin, Bangyang Wei, Yihang Ding et al. (+2 more)
Task-specific fine-tuning can rewrite a
language model's answers beyond the training task, complicating updates that must preserve existing behavior. We introduce ATLAS, which turns retained-domain representations into an input-dependent rule for task adaptation. An activation atlas supplies local reference centers and directional filters to a shared low-rank residual. Target supervision learns the residual, while retained geometry shapes its action throughout training and inference. On Qwen3-8B, ATLAS achieves lower mean retained-output Kullback-Leibler (KL) divergence than all seven published baselines at shared coding-performance requirements, with consistent advantages across multiple training seeds. Structural comparisons identify the contributions of retained reference states and directional conditioning, and answer-level analyses show fewer rewritten mathematical answers and more stable commonsense choices. Experiments spanning five backbones and two retained domains further demonstrate coding gains with reduced retained-output movement. With compact storage and modest decoding overhead, ATLAS provides a practical mechanism for acquiring specialized skills while maintaining continuity in existing responses.
Read the full abstract ▾
All authors Jiangtao Lin, Bangyang Wei, Yihang Ding, Siyi Liu, Yuhan Dong
Machine Learning
Causal Routing for Unlearning
Bardh Prenkaj, Andrea D'Angelo, Davide Mottin et al. (+4 more)
LLMs cannot forget the way we delete a file. Strangely, we are asked to remove something that was never put anywhere in particular. What the model took from a piece of text is now smeared across billions of weights. Existing methods rewrite all of them to change one thing, and none of them say which part produced that change. To address this, we introduce Causal Routing for Unlearning (CRU) by asking where the concept is expressed in the model and suppressing only that part. One untrained forward pass over the forget set ranks
neurons by how their activations vary. Then, small routing modules on those
neurons gate and suppress only the concepts that need to be forgotten. In CRU, the base model is frozen, and any change in behavior is caused only by the gated
neurons; hence, why the routing is causal. Due to our parameter efficiency (only ~0.01% as many parameters as the base model), unlearning a concept costs 14 GiB, whereas the baselines require 71 GiB. On TOFU, CRU is indistinguishable from the retained model (p > 0.05, KS test) and is never Pareto-dominated, whereas every compared baseline matches its forgetting on the larger-forget batches only by collapsing utility. On RWKU, it achieves an
adversarial-probe recall of 0.052, compared to 0.250 for the strongest baseline, meaning the knowledge is gone, not merely harder to reach. Thus, deciding on the intervention at query time, rather than fixing it beforehand, is the axis along which we argue that unlearning should proceed.
Read the full abstract ▾
All authors Bardh Prenkaj, Andrea D'Angelo, Davide Mottin, Federico Fontana, Davide Gabrielli, Paola Velardi, Stefano Faralli
Machine Learning
Deep kernel hedging
Jean-Loup Dupret, Donatien Hainaut and Edouard Motte
We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods. The hedging functional is restricted to a reproducing kernel
Hilbert space whose kernel is parameterized through a neural network
embedding of the input features. The framework minimizes a regularized empirical risk under convex loss functions and can accommodate path-dependent information through truncated time-augmented signature features. We derive a generalized representer
theorem for the joint hedging problem, reducing the empirical optimization to a finite-dimensional problem. To further reduce the computational cost associated with large kernel
matrices, we develop a scalable random
Fourier feature approximation and establish convergence guarantees. The random
Fourier parameters are sampled once and remain fixed throughout training, while the deep kernel adapts to
market data through the learned neural representation. We evaluate the performance of the proposed deep kernel approach on both synthetic and real data and compare it with standard kernel methods and classical deep hedging architectures. Numerical results indicate competitive and robust hedging performance, particularly in low-data regimes, which highlights the benefits of combining expressive neural representations with the inductive bias of kernel methods.
Read the full abstract ▾
Software Engineering
From Noisy Telemetry to Actionable Warnings: GPU Failure Prediction in Industrial Clusters
Yongqian Sun, Run Zhu, Wenwei Gu et al. (+9 more)
GPU clusters are critical infrastructure for AI services, but accurate and actionable GPU failure prediction remains a problem in production settings. We study ticket-linked telemetry from a ByteDance GPU cluster and identify three obstacles: workload-confounded telemetry, heterogeneous fault precursors, and the gap between window-level predictions and actionable alerts. These findings motivate Falcon, a fault-specific warning framework combining missingness-aware temporal and peer-relative features, fault-specific learner selection, and an event policy based on thresholding, persistence, and cooldown. On the test set, Falcon achieves the highest F1 among four baselines and reaches 70.6% F1 on the best-performing fault type. Detected cases provide median lead times of 17.34-35.57 hours. We further report a production deployment, where Falcon is calibrated toward high-precision alerts to reflect false-positive costs. Together, these results show that fault-specific modeling improves early warning from noisy production GPU telemetry.
Read the full abstract ▾
All authors Yongqian Sun, Run Zhu, Wenwei Gu, Mengyao Li, Shenglin Zhang, Guanjin Wang, Yang Zhang, Xin Wu, Linlin Han, Feng Wang, Xiaozhou Liu, Yu Zhang
Computer Vision
VL-AcneSeg: A Vision-Language Framework for Region-Aware Acne Lesion Segmentation
Sukju Oh, Soo Ick Cho, Dae Hun Suh et al. (+1 more)
Acne assessment is crucial for clinical decision-making, yet traditional grading and counting are subjective and fail to account for lesion size. While area-based assessment has emerged as a promising alternative, acne
segmentation has continued to rely on general-purpose architectures. To address this gap, we propose VL-AcneSeg, a
multimodal framework for acne lesion
segmentation that leverages CLIP and region-level text
prompts to incorporate spatial priors, enabling lesions to be localized across the whole face. Because region-level
prompts indicate which facial areas contain lesions, we report a single global
prompt, which requires no such information, as our primary setting. On our internal clinical
dataset, VL-AcneSeg achieves a Dice score of 0.5082 and an IoU of 0.3407 under this protocol, the highest among all compared methods, including recent
vision-
language segmentation methods that are themselves given region-level
prompts; region-level prompting raises these to 0.5296 and 0.3602. Moreover, lesion area measurements derived from our
segmentation correlate with IGA scores at a level comparable to expert annotations (Pearson r = 0.719 versus 0.658). Notably, our framework maintains consistent performance across external validation
datasets, performing reliably even on uncontrolled smartphone images without requiring additional training or fine-tuning. By pairing a protocol that requires no lesion-location information with area-based severity estimation, this work provides a foundation for objective acne assessment outside the clinic. Our implementation is publicly available at: https://github.com/sukjuoh/VL-AcneSeg
Read the full abstract ▾
All authors Sukju Oh, Soo Ick Cho, Dae Hun Suh, Sukkyu Sun
Discrete Mathematics · Cross-listed from math.CO
Three Standard Deviations Suffice While One Does Not
Victor Reis and Zhao Song
Spencer's 1985 “six standard deviations suffice”
theorem shows that every $A \in [-1,1]^{n \times n}$ has a sign vector $x \in \{-1,1\}^n$ with $\|Ax\|_\infty \le 6\sqrt{n}$. We show the upper bound $\sqrt{3\operatorname{arsinh}(10)}\sqrt{n}+4 < 2.9992 \sqrt{n} + 4$ by directly rounding the minimizer of a potential function to a vertex of the cube. We also show that, for every power of two $n \ge 2^{50}$, there exists a
matrix $A \in \{-1,1\}^{n \times n}$ such that $\|Ax\|_\infty >1.0000002\sqrt{n}$ for every choice of signs $x \in \{-1,1\}^n$. The construction simply replaces a $2^{-22}$ fraction of the columns of a Hadamard
matrix with independent random sign vectors. This is the first improvement over the $\sqrt{n}$ lower bound of Olson and Spencer (1978), which uses a Hadamard
matrix.
Read the full abstract ▾
Computer Vision
Precise Editing and Flexible Referencing for Interactable Worlds
Xinyao Liao, Xianfang Zeng, Zhu Liang et al. (+5 more)
We present EditWorld, a
video world model for precise editing and flexible referencing in interactable worlds. Existing
video world models primarily focus on
navigation, letting users explore generated worlds but offering limited control over how existing world content is modified. EditWorld extends world modeling from exploration to precise modification by streaming editing instructions and reference images during autoregressive generation. To support these capabilities, EditWorld introduces Gated Causal
Attention for temporally varying editing conditions and reference images, together with a Sparse Context mechanism that maintains a bounded historical context for long-horizon inference. We further adopt joint autoregressive and bidirectional training with annealed self-resampling, and construct a dedicated data synthesis and annotation pipeline that provides supervision for world editing. We also present WBench-Editing to systematically evaluate streaming world editing capabilities. EditWorld achieves the best overall performance on WBench-Editing with an overall score of 73.8 and an editing score of 80.0, substantially outperforming existing methods on editing-related metrics. https://github.com/leoisufa/EditWorld
Read the full abstract ▾
All authors Xinyao Liao, Xianfang Zeng, Zhu Liang, Zhoujie Fu, Qianxun Xu, Jiachi Liu, Gang Yu, Guosheng Lin
Software Engineering
The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing
Zhiwen Wu and Chengxu Wu
A small Office edit creates two obligations: propagate every required update and leave protected state untouched. Updating too little leaves dependencies inconsistent; updating too much changes content the user did not authorize. We introduce OfficeEditBench, a 170-task
benchmark for change-scoped maintenance of spreadsheets, presentations, and documents. Task contracts specify required updates, protected state, native structures, and applicable interaction requirements. Across 510 archived task-system outcomes from WorkBuddy, Doubao, and Codex, we distinguish file delivery, target completion, and verifier-defined acceptance. Hard package-valid delivery ranges from 92% to 100%, yet no selected output satisfies the complete contract. Case analysis highlights why local correctness is insufficient: an updated value can lose its generating formula, a revised rule can fail to reach related conclusions, and a new deadline can omit a retained prerequisite. These mechanisms connect artifact-level checks to the continued maintainability of Office files. We analyze maintenance failures while distinguishing frozen automatic verdicts from human acceptability. OfficeEditBench provides a testbed for completing required changes while preserving the logic and scope of existing work.
Read the full abstract ▾
Machine Learning
Shengchao Hu, Peng Wang, Qiyang Zhou et al. (+5 more)
Recent advances in
Vision-
Language-Action (VLA) models point toward general-purpose robotic intelligence by unifying perception, instruction, and control. Despite impressive progress, existing VLA models often adapt poorly due to tri-modal misalignment among
vision,
language, and action, which weakens action grounding and hurts generalization and fine-tuning efficiency. In this work, we present
Alignment-Guided Flow
Transformer (AGFT), a novel framework that explicitly enforces tri-modal
alignment through a dedicated
alignment loss, bridging the representational gap across modalities and enhancing task adaptation. While prior research has predominantly emphasized bi-modal
vision–
language alignment, we systematically formalize and study tri-modal
alignment in VLA models, and provide both ablations and analysis to isolate its role in improving adaptation and robustness. To further accelerate deployment, we adopt a flow-matching objective, enabling substantially fewer inference steps than
diffusion-based policies while maintaining accuracy. Theoretically, we establish a quantitative connection between the tri-modal
alignment gap and the optimization tightness of flow matching; empirically, experiments on the extensive
benchmark show that AGFT achieves superior success rates and lower inference latency compared to SOTA baselines, underscoring tri-modal
alignment as a key ingredient for scaling robust VLA manipulation.
Read the full abstract ▾
All authors Shengchao Hu, Peng Wang, Qiyang Zhou, Guodong Zheng, Yuqi Huang, Li Shen, Ya Zhang, Dacheng Tao
Machine Learning
PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models
Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier et al. (+2 more)
Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with diagnosis, this acquisition provenance can become a shortcut, yet the usual evidence, shifted transfer and provenance decodability, does not show whether a predictor uses it. We introduce PhysioTRACE, a four-axis behavioral audit for frozen encoders that separates what a probe can decode from what a fixed task head relies on. Recover scores how decodable provenance is; Stress reverses only the provenance-target association on the same held-out records; Intervene removes a train-localized provenance component; and Verify certifies that removal only if it beats matched random projections within a declared utility margin. Each audit thus ends in one of three verdicts: no reliance, or reliance with the remedy certified or refused. Across
EEG and ECG, five training objectives, and five frozen foundation models, the relation between Recover's calibrated score and out-of-distribution utility changes sign between
datasets, so neither can stand in for a reliance test. On paired
EEG views where the shortcut is known by construction, the audit detects it (the exposed head loses about 0.2 AUROC when the association is reversed, while a control head is unaffected) and certifies removal of a rank-two component that restores control-level behavior without measurable utility loss, for both encoder objectives tested. On real ECG device metadata it returns all three verdicts: it certifies a remedy that removes 91% of one model's excess vulnerability, finds no reliance where device and diagnosis are barely associated, and refuses the remedy for a second model whose localized direction also carries task signal. Robustness to how inputs were recorded therefore needs a behavioral test, and PhysioTRACE provides one that can pass, fail, or refuse a remedy.
Read the full abstract ▾
All authors Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier, Xue Liu, Kun Zhang
Cryptography and Security
CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents
Xiao Yang, Yangchen Ou, Yuhan Gao et al. (+3 more)
Large
language model (LLM)-based
agents increasingly rely on external tools and content, exposing them to indirect
prompt injection (IPI). This threat has motivated a wide range of defenses, among which training-based defenses are often regarded as most reliable. However, existing training-based defenses are typically optimized on a static distribution of explicit injections. They learn surface-form cues rather than the boundary between serving the user and obeying an injected objective, and therefore fail when malicious intent is folded into a plausible workflow and deferred for several turns. We present CoDeL, a defense that hardens
agent against an attack distribution it reshapes as it trains. The defender is updated each round via LoRA-based GDPO under a decoupled reward over safety, task progress, and format compliance, so refusing injections and completing the user's task jointly define fitness. To keep supplying it with the failures worth learning from, a co-evolving prober searches over injection rounds, attack methods, and payloads for injections that still penetrate the current defender, guided jointly by attack success and attack latency so that it preferentially mines breaches the defender notices too late. Each defender update invalidates part of the attack population and forces the next round onto a new frontier, turning the defender's own failures into a moving curriculum. Extensive experiments on three IPI
benchmarks, nine baselines, and two base models show that CoDeL reduces attack success rate (ASR) by 88.5% and outperforms other baselines largely (+38.0%). Codes are available.
Read the full abstract ▾
All authors Xiao Yang, Yangchen Ou, Yuhan Gao, Le Wang, Zonghao Ying, Aishan Liu
Computational Complexity
A Quadratic Lower Bound on Determinantal Complexity
Mrinal Kumar and Ben Lee Volk
We prove an $\Omega(n^2)$ lower bound on the determinantal complexity of the power sum
polynomial $\sum_{i=1}^n x_i^n$ over the field of complex numbers. A similar result was claimed in a recent paper of Sheshadri (arXiv:2606.13628), via an AI-assisted and AI-written proof. Assuming its correctness, this was the first super-linear lower bound for this fundamental algebraic problem for any explicit
polynomial. However, the authors of this note were unable to follow the details and verify the argument in arXiv:2606.13628, in spite of considerable effort on their part. The proof we provide here is short, (almost) self-contained and seemingly simpler.
Read the full abstract ▾
Artificial Intelligence
When Does Structured Knowledge Help Neural Theorem Proving?
Sareh Nabi, Roland Vogl and Marzieh Nabi
Does structured mathematical knowledge help LLMs prove
theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib encode 285,000+ verified
theorems with syntactic dependencies, but the semantic layer mathematicians rely on for discovery (analogies, generalizations, cross-domain bridges) remains implicit. We introduce MathAgent, which builds this layer as a knowledge graph, MathKG, and uses it to augment LLM
theorem provers. MathKG connects 364 Mathlib
theorems and definitions by 9,434 typed semantic edges inferred via LLM-based relation extraction anchored to verified Mathlib declarations. We run a controlled ablation across four augmentation modes (no context, knowledge-graph context, Mathlib
retrieval, both) and five models: Qwen3-8B/32B, their Lean-specialized derivatives Goedel-Prover-V2-8B/32B, and Claude Sonnet 4.6, on miniF2F, plus PutnamBench and MathOlympiadBench for Sonnet. Three findings emerge. (i) Specialization dominates augmentation: Lean fine-tuning adds 33-38 percentage points of solve rate in every mode, and a specialized 8B model beats a $4\times$ larger general one by 29-35 points, while no augmentation mode improves solve rate by more than 3 points. (ii) Augmentation is capability-conditioned: knowledge-graph context helps small models but hurts large ones, with the specialized model gaining more relative to its general base at every scale. (iii) Yet the augmentation modes solve different problems: an oracle selecting the best mode per problem solves 6% to 58% more than the unaugmented prover, a complementarity effect that strengthens on harder problems (32% more on PutnamBench). These results motivate adaptive strategies that select augmentation by model capability and problem. Code, data, and artifacts are available at https://github.com/sarehnabi/mathagent
Read the full abstract ▾
Artificial Intelligence
Escaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning
Yijie Sun, Sanquan Sun, Yanda Zhu et al. (+3 more)
Efficient cooperation is challenging due to the usual partial observability of each
agent in multi-
agent reinforcement learning. Recurrent networks encode local interaction histories, but their hidden representations provide limited insight into the information underlying individual decisions. To address these challenges, we propose a novel interpretable framework, called escaping local views (ELV), which introduces semantically structured latent concepts to render policy decisions transparent. Specifically, each
agent extracts low-dimensional semantic concepts from its local observation and action-observation trajectory. These concepts are jointly encoded into a contextual latent variable via a variational autoencoder (VAE), which builds a bridge between local views and global semantics. To explicitly model the decision of each
agent, we employ a dual-path
attention mechanism in which one module estimates the salience of individual concepts relative to the global context, while the other captures higher-order cooperative patterns with pairwise concept interactions. Furthermore, we incorporate a concept prediction module that derives an intrinsic reward from next-concept prediction errors, which incentivizes
agents to explore regions of semantic novelty. Experiments in multiple environments verify that ELV not only achieves competitive performance but also explicitly provides how
agents reason about their decisions.
Read the full abstract ▾
All authors Yijie Sun, Sanquan Sun, Yanda Zhu, Yuanyang Zhu, Yaohua Hu, Chunlin Chen
Artificial Intelligence · Cross-listed from stat.ML
Understanding Generalization Requires Universal Induction
Aram Ebtekar, Marcus Hutter and Danica J. Sutherland
Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases that it cannot justify. No Free Lunch (NFL)
theorems force any learner that beats chance on some environments to underperform on others. We might hope that past experience informs which environments to expect, but NFL applies equally to meta-learning. Thus, any method that makes meaningful predictions necessarily begins with an inductive bias external to the data. Choosing to bias toward short programs yields Solomonoff induction (SI), whose performance is competitive against all computable learners - albeit up to "constants" that become large when comparing against specialized methods that exploit background information. We therefore relativize SI to an information vantage point, biasing toward short programs with access to all preexisting information. This reframes the inductive bias: instead of seeking some absolute notion of simplicity, we favor accessibility with respect to our vantage point. An
algorithm can only outpredict the relativized SI to the extent that its code contains additional information about the data, and no
algorithm can generate such information. While SI is incomputable and hence not a practical
algorithm, it provides a formal optimum for inference in the limit of infinite compute, and there is evidence to suggest that frontier AI systems roughly approximate it. Thus, the only known answer to meta-NFL is rooted in algorithmic information theory, which we should expect to play a fundamental role in explaining the generalization behavior of modern (and future) AI systems.
Read the full abstract ▾
Machine Learning
ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models
Hai Duong, Thanh Le and ThanhVu Nguyen
Transformer-based models are widely used for
reasoning, coding, and
multimodal agentic tasks. To provide formal assurance of desirable behaviors, such as robustness, safety, and
fairness, neural network verification techniques prove required properties and provide auditable guarantees before deployment. However, prior work remains limited to small or restricted
Transformers, and maintaining precision across deep models remains challenging. In this work, we introduce ZonoGpt, an abstract domain for verifying large
transformers that maintains a space complexity independent of network depth. ZonoGpt uses a structured zonotope and a generator reduction mechanism to efficiently preserve correlations. To maintain precision, it introduces block-specific fused transformations for
Attention and LayerNorm that retain feature relations, along with an affine transform for GELU that preserves generator relations. These mechanisms enable ZonoGpt to be the first approach to verify standard architectures, scaling to official HuggingFace models up to GPT-2 Medium (24 blocks, 300M+ parameters) and successfully verifying 1,339 instances across text and
vision tasks.
Read the full abstract ▾
Cryptography and Security
Breaking Windows Malware Detection: A Comprehensive Evaluation of Problem-Space Adversarial Robustness
Mashal Zainab, Salijona Dyrmishi, Hamid Bostani et al. (+2 more)
Problem-space evasion attacks have exposed critical weaknesses in machine learning-based malware detectors; yet, their evaluation remains fragmented across models,
datasets, and attack methodologies, often neglecting domain-specific requirements such as executability and functionality preservation. We address this gap with a unified, large-scale evaluation of nine state-of-the-art evasion attacks against eight Windows malware detectors, including seven open-source models and one commercial detector, under executability-preserving conditions. Our study analyzes attack effectiveness, complementarity, transferability, and
adversarial hardening to evaluate robustness along complementary dimensions. We show that detector vulnerability depends strongly on both model representation and attack type: raw-byte detectors are particularly susceptible to several classes of problem-space manipulation, but no detector family is uniformly robust across all attacks. Importantly, effectiveness is not explained by transformation-space size alone: the strongest attacks can achieve substantially higher success while using fewer distinct transformations and concentrating on a small set of high-impact manipulations. We further show that two complementary attacks are sufficient to cover approximately 99% of the
adversarial examples produced by the remaining evaluated attacks. Transferability exhibits a different pattern from direct attack success: attacks with low direct success can produce highly transferable evasions. Finally,
adversarial hardening is highly attack- and model-dependent: robustness gains often fail to transfer across attacks and can even increase susceptibility to unseen attacks. These findings highlight limitations in current malware robustness evaluations, establish a comprehensive empirical baseline, and clarify relationships between effectiveness, transferability, and defense robustness.
Read the full abstract ▾
All authors Mashal Zainab, Salijona Dyrmishi, Hamid Bostani, Lorenzo Cavallaro, Maxime Cordy
Computation and Language
RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications
Jianpeng Zhao, Haihua Xu, Haoyang Zhang et al. (+7 more)
We study
reasoning in Rule-Governed Decision Tasks (RGDTs), where models apply external rules to case facts and justify decisions, as required in policy, contract, and compliance settings. Beyond the deductive capability emphasized by standard mathematical and logical
reasoning tasks, RGDTs require interpreting rules and their applicability, assessing conditions from evidence, combining judgments under rules and exceptions, and providing checkable justifications. These demands motivate a
benchmark assessing both decisions and their stated grounds. We introduce RGDT-Bench, providing 202.1K condition-level supervision slots across four task tracks and eight supported task-probe combinations that vary access to supporting information. Label-blind extraction and deterministic checks produce labels for warrant completeness: source-referenced coverage and consistency of stated decision grounds. The
benchmark attributes failures to four process layers: rule use, condition, evidence, and aggregation, and checks the final outcome. Among evaluable correct responses, warrant incompleteness averages 40.2% across six evaluated LLMs and supported task-probe combinations. Such warrant incompleteness poses potential safety risks and remains difficult to detect: the best of seventeen existing evaluators reaches only 57.69% (random: 50%) task-averaged area under the receiver operating characteristic curve (AUROC). To address this difficulty, we train a simple reward model with warrant supervision. It achieves 69.24% task-averaged AUROC among correct answers, exceeding the matched outcome-supervised baseline by 10.37 pp (percentage points) and the best existing evaluator by 11.55 pp. Beyond completeness assessment, the model outperforms both outcome-supervised baselines across nearly all response-selection comparisons, supporting RGDT-Bench's warrant supervision for RGDT
reasoning.
Read the full abstract ▾
All authors Jianpeng Zhao, Haihua Xu, Haoyang Zhang, Shuang Qian, Yixiang Tang, Xintao Wang, Kun Sun, Pei Wu, Shuhan Zhong, Pengyang Wang
Computation and Language
When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation
Yekun Xu, Ante Wang, Jingyi Ren et al. (+3 more)
Confidence estimation is crucial for developing trustworthy large
language models (LLMs), with most methods following
estimator-based or verbalization-based paradigms. While recent research increasingly focuses on improving verbalized self-reports of confidence, we challenge the prevailing view that this approach surpasses independent confidence
estimators. Our empirical study shows that a dedicated confidence
estimator can substantially outperform verbalized confidence, indicating that LLMs' internal representations contain richer confidence signals. Building on this finding, we propose Iterative Policy-
Estimator Training (IPoET), a framework that synergizes the complementary strengths of verbalized
reasoning traces and informative representations. IPoET alternates policy optimization with
estimator updating, integrating
estimator-derived confidence feedback into policy learning and refreshing the
estimator on new policy rollouts. Experiments across diverse
datasets and Qwen and Llama backbones demonstrate that, by iteratively exploiting richer hidden features and adapting to the evolving policy distribution, IPoET consistently outperforms both
estimator- and verbalization-based baselines in-domain and achieves superior or comparable results across all out-of-domain metrics. For more details, refer to https://github.com/xyk829/ipoet.
Read the full abstract ▾
All authors Yekun Xu, Ante Wang, Jingyi Ren, Xuanyi Chen, Weizhi Ma, Yang Liu
Machine Learning
SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning
Seunghyun Yoo, Kiseok Kim, Hyeontae Joo et al. (+2 more)
This study addresses the catastrophic forgetting problem that occurs when sequentially learning successive tasks using Low-Rank Adaptation (LoRA) from a lifelong learning perspective. While existing approaches have primarily constrained parameter updates or learning subspaces to reduce interference with past knowledge, they have not fully considered additive interference. This occurs when a newly added residual adapter on top of a fixed past model generates non-zero responses along input directions important for old tasks, thereby altering previous predictions. To this end, we propose Subspace Protection with Allocated Capacity for Efficient Continual Adaptation (SPACE-LoRA). SPACE-LoRA directly suppresses the responses of the new residual branch along input activation directions that are important for old tasks and adaptively determines the protection coverage for each module based on past-task sensitivity estimated via a common Fisher sensitivity-based coverage target. Under a fixed LoRA rank, this approach adaptively adjusts module-specific protection coverage while suppressing interference along input directions sensitive to old tasks. We assess the effectiveness of activation-subspace protection in mitigating catastrophic forgetting and examine the role of sensitivity-guided protection in continual learning across diverse tasks. Code is available at https://anonymous.4open.science/r/SPACE-LoRA-7864.
Read the full abstract ▾
All authors Seunghyun Yoo, Kiseok Kim, Hyeontae Joo, Junyeop Bang, Hwangnam Kim