Artificial Intelligence · Cross-listed from cs.RO
Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies
Xingyu Lin, Zhuang Li, Zhongrun Wu et al. (+2 more)
Vision-
language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish whether their physical executions agree. We study cross-policy end-effector geometry in 15,000 closed-loop LIBERO rollouts from four policies. The primary clean-condition analysis forms 3,600 configuration-matched, and therefore dependent, policy pairs. Both-success pairs have a median normalized dynamic time warping distance of 0.0120 m versus 0.0380 m when exactly one policy succeeds. This ordering holds in every task, every policy pair, and nine sampling and band-limited representations; however, the ratio varies severalfold across representations, so we report the direction rather than a fixed multiple. Both-failure pairs are more separated again but rest on thin, uneven support, so we report them as exploratory. Within successful executions, partner replacements separate more across tasks than across initial states. A matched baseline still reveals measurable, heterogeneous residual policy differences, so a low cross-policy distance does not imply interchangeability. Successful executions sit about as far from same-task demonstrations as those demonstrations sit from each other, compatible with task-associated geometry without separating training-data overlap from task constraints. A common 72-action window preserves the ordering but reduces its magnitude; endpoint and duration adjustment likewise leaves a positive mixed-outcome coefficient relative to both-success pairs, though its magnitude is specification-dependent. Under composite visual stress, policy rankings and pair composition change together.
Read the full abstract ▾
All authors Xingyu Lin, Zhuang Li, Zhongrun Wu, Shouquan Zhou, Dehui Du
Artificial Intelligence · Cross-listed from cs.RO
SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
Hiroaki Kingetsu, Hiroaki Kurihara, Kaoru Yokoo et al. (+2 more)
Fine-tuning
Vision-
Language-Action (VLA) models commonly relies on human teleoperation demonstrations, while reinforcement learning (RL) with sparse binary rewards faces an exploration challenge when successful trajectories are rarely sampled. We propose SynthDemo-RL, a teacher-student framework in which an automated teacher converts simulator-privileged state into successful manipulation trajectories, a VLA student is distilled from them by supervised fine-tuning (SFT), and PPO with binary task-success rewards refines the student. We study reward coverage, the fraction of tasks for which at least one success is observed under the fixed evaluation protocol, as a complement to the average success rate. On LIBERO-PRO, a public
benchmark of perturbed LIBERO tasks for which no demonstrations exist, 27 of 57 scored tasks are at exactly 0% success for a pi_0.5 policy fine-tuned on the original LIBERO tasks. Direct PPO from this policy, under the same PPO recipe and the same RL compute as SynthDemo-RL's refinement stage, rescues 10 of these 27 tasks and leaves 17 at 0%. SynthDemo-RL, with 50 synthesized trajectories per task and no new human demonstrations, rescues all 27 and reaches average success rates of 97.8% and 97.1% on the Position and Task axes of LIBERO-PRO, respectively. On standard LIBERO, the same pipeline reaches 96.0% with no human demonstrations, within 1.7 points of pi_0.5 trained on 50 human demonstrations per task. We further validate the pipeline on RoboTwin 2.0 and verify that trajectories from a policy trained in a MuJoCo twin execute open-loop on a physical
robot.
Read the full abstract ▾
All authors Hiroaki Kingetsu, Hiroaki Kurihara, Kaoru Yokoo, Kenji Fukumizu, Manohar Kaul
Artificial Intelligence · Cross-listed from cs.CL
Chinese Competitive Debating Dataset and Benchmark
Zongrui Yang, Haoyuan Li, Zhongsheng Wang et al. (+5 more)
Debate adjudication requires tracking how arguments develop through interaction, yet existing
datasets rarely combine fine-grained debate transcripts with professional judgments collected during real competitions under a shared rubric. We introduce a
dataset and
benchmark for evaluating large
language models' understanding of competitive Chinese-
language debate at the match, stage, and speaker levels. We organized 182 matches and recruited 120 professional judges, with each match independently adjudicated by three judges using a predefined rubric. After excluding matches with incomplete records, the
dataset contains 148 matches, 2,698 stages, and 20,542 exchange units, with manually verified transcripts and
segmentation. It preserves original stage scores, match votes, best-debater ballots, and adjudication rationales. We define three tasks: winner-tendency prediction, stage-score prediction, and best-debater prediction. Zero-shot evaluation of multiple large
language models yields a highest winner-prediction accuracy of 66.2%, a highest Pearson correlation of 0.250 between model stage scores and mean human ratings, and a highest best-debater prediction accuracy of 56.8%. The
dataset and
benchmark provide a testbed for studying large
language models' understanding of interactive argumentation and their agreement with professional judges.
Read the full abstract ▾
All authors Zongrui Yang, Haoyuan Li, Zhongsheng Wang, Zhirui Zeng, Pengqian Han, Yi Zhou, Yuting Wang, Jiamou Liu
Artificial Intelligence · Cross-listed from cs.CL
Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
Hans Andersen and David Dichas
Recent work applies human psychometric questionnaires to large
language models to elicit moral and value profiles, but it is not clear whether these instruments measure anything stable in models or whether the resulting profiles can be moved toward a target human population. We administer the Norwegian Moral Foundations Questionnaire (MFQ-30) to six open-weight LLMs and compare their foundation profiles to a sample of N = 1,282 Norwegian respondents. We test two steering interventions,
prompt-level persona steering and activation-level ActAdd. Half the models engage with the questionnaire under our
attention check. The other half default to flat or central-tendency outputs that look near-human on average without tracking item content. A neutral Nordic-respondent persona, written without any distributional information from the human sample, brings the engaging models 44-77% closer to the Norwegian mean in Mahalanobis $d^2$. One-pair ActAdd at a fixed mid-layer flattens the foundation profile rather than steering individual foundations. For at least one model the same persona that shifts the profile also induces engagement that was absent at baseline, a concrete instance of the cognitive phantoms that Peereboom et al. (2025) warn about.
Read the full abstract ▾
Artificial Intelligence
One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction
Hongliang Li, Lu Wang, Yong Xu et al. (+6 more)
Large
language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differently for each user. Existing
prompt optimization methods, however, rely on a single
prompt optimized against a global objective, which is misaligned with the inherent user heterogeneity of real workplaces. We formulate enterprise IE as per-user
prompt adaptation under interaction feedback and propose Self-Meta-Evolve, a hierarchical framework that maintains a dedicated
prompt for each user and continuously refines it through a dual-loop process: an inner loop that edits structured
prompts based on persona-conditioned feedback, and an outer loop that evolves the meta-
prompt itself by distilling successful editing patterns. To enable scalable training and evaluation, we release a persona-driven IE
benchmark of 292 simulated enterprise users, paired with a reproducible persona-generation pipeline grounded in O*NET occupational taxonomies. On this
benchmark, Self-Meta-Evolve achieves a 74.58% success rate, outperforming the strongest
prompt-optimization baseline by 13.56 absolute points, and reaches 52.54% within only two iterations. A double-blind human study with twenty real professionals further confirms that
prompts adapted by our framework win against static baselines in 71% of pairwise comparisons.
Read the full abstract ▾
All authors Hongliang Li, Lu Wang, Yong Xu, Hanyang Chen, Zhitao Hou, Xiaoting Qin, Song Ge, Qingwei Lin, Dongmei Zhang
Artificial Intelligence
Calibrating Teacher–Student Discrepancy for On-Policy Distillation
Qiangqiang He, Jin Li and MingCai Chen
On-policy
distillation (OPD) improves
reasoning models by learning the
token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does not purely reflect the capability gap between the teacher and the student: it also contains deviations arising from the teacher itself, which are consequently mixed into the observed teacher–student discrepancy and indiscriminately learned by standard OPD during training. This issue is further exacerbated by privileged OPD, where privileged information induces larger teacher-side likelihood shifts, thereby encouraging the student to learn more of the teacher's own deviation. We introduce Calibrated On-Policy
Distillation (Cal-OPD), which estimates the teacher's self-deviation region through positive and negative privileged interventions and calibrates the original teacher–student discrepancy by retaining only the component that lies beyond this region. Experiments on mathematical
reasoning benchmarks show that, while retaining only about 52–65% of the original teacher–student discrepancy as the optimization signal, Cal-OPD consistently outperforms standard OPD and its variants across model scales.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation
Xinyu Liu, Gökhan Solak and Arash Ajoudani
Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both task strategy and low-level motion generation. In this setting, the action representation is critical because it determines how policy outputs are converted into
robot motion, shaping both exploration and physical execution. Direct Cartesian command interfaces require the policy to generate motion at every decision step, coupling task-level adaptation with continuous low-level control and increasing the learning burden. We propose PA-RL, a reinforcement-learning framework that uses artificial potential fields as the action representation. Instead of commanding motion directly, the policy adapts the parameters of an energy-like potential field, which generates a state-dependent guidance direction executed through a Cartesian impedance controller. We evaluate PA-RL on peg-in-hole insertion, a representative contact-rich task with nonlinear dynamics and discontinuous contact transitions. In simulation, PA-RL is compared with Cartesian velocity, Cartesian pose, and variable-impedance action spaces using the same RL
algorithm. PA-RL is the only method to reach a 100% evaluation success rate within the allotted training time, while the best baseline reaches 92.6%. It also reduces joint-torque variation by 55.4% and Cartesian acceleration variation by 70.8% relative to the best baseline, without explicit motion-quality penalties in the reward. The simulation-trained policy further completes 9/9 real-
robot insertions without fine-tuning, demonstrating the deployment feasibility of the learned potential-field interface.
Read the full abstract ▾
Artificial Intelligence
Reducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education
Andy Gray and Jake Hobbs
Access to academic support is a key determinant of student success, yet students experience it unequally: some readily seek help from lecturers or tutors, while others hesitate due to anxiety, fear of judgement, uncertainty about expectations, or low confidence in their understanding. This may be especially evident in computing education, where programming tasks are cumulative and cognitively demanding. Although students increasingly turn to general-purpose generative AI tools, these can produce responses that are inaccurate, insufficiently contextualised, or misaligned with module expectations. This study presents and evaluates Beacon, a course-specific
Retrieval-Augmented Generation (RAG) system providing private, immediate, module-aligned academic support. Grounding responses in approved teaching materials, Beacon was designed to lower barriers to help-seeking while encouraging independent learning. Using a design-based research approach, Beacon was developed iteratively and evaluated via mixed methods, combining questionnaires and semi-structured interviews with students and staff at a Higher Education institution. Students described Beacon's responses as closely aligned with module content and more trustworthy than unrestricted generative AI tools, valuing its use of pseudocode and scaffolded explanations over direct solutions. Although participants remained cautious about trusting AI-generated responses without verification, they viewed the system as a valuable first point of support before consulting lecturers or official resources. The findings suggest that carefully designed course-specific AI systems may reduce barriers to academic support by occupying an intermediary space between independent study and formal support. Rather than replacing educators, educational AI may be most valuable when it broadens access to guidance while preserving the pedagogical role of lecturers.
Read the full abstract ▾
Artificial Intelligence
Beyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection
Syed Ali Ahmed, Malaika Raza, Muhammad Shoaib Siddiqui et al. (+1 more)
Fraudulent job posting detection aims to identify job advertisements that are corrupted either through fake content, misleading information, or negative intent, disrupting the online eco-system of job-seekers and employers. Existing studies in this domain lack effective methods to simultaneously achieve high accuracy and meaningful structure of latent-space representations that capture subtleties among fake posts. To this end, we propose Centroid-Guided Contrastive Loss (CGCL), a loss function which unifies classification with densely formulated clustering to consistently reshape latent-space through a centroid-driven top-$k$ push-and-pull mechanism. The complementary nature of CGCL enables the model to enforce accurate decision boundaries and maintain high clustering compactness, effectively capturing both class separability and latent structure. Extensive experiments demonstrate the state-of-the-art (SOTA) performance of our method on EMSCAD, a public
benchmark dataset. The code associated with this work is available at: https://github.com/ali-ahmed925/CGCL_code
Read the full abstract ▾
All authors Syed Ali Ahmed, Malaika Raza, Muhammad Shoaib Siddiqui, Muhammad Rafi
Artificial Intelligence · Cross-listed from cs.CR
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
Pedro Pereira, Eva Maia and Isabel Praça
Retrieval-Augmented Generation (RAG) improves large
language models by grounding outputs in external knowledge sources, but this dependency also creates a surface for poisoning attacks. This paper introduces Micro-Collaborative Poisoning, a distributed attack in which a false target claim is divided across multiple locally plausible documents instead of being concentrated in a single malicious passage. We evaluate the attack across 108 RAG configurations by varying
dataset, retriever architecture,
retrieval depth, database composition, number of poisoned databases, and generator model. The results indicate that Micro-Collaborative Poisoning is not driven by a single dominant poisoned passage, but by the accumulation of weak
adversarial signals across retrieved sources. Increasing top-$k$ and poisoning multiple databases make it more likely that these signals will appear together in the retrieved context, while clean database diversity and stronger retrievers can reduce their influence. The document-level poisoning visibility analysis further shows that this threat is difficult to expose through isolated document inspection, since Micro-Collaborative Poisoning achieves downstream influence while leaving a weaker explicit poisoning signature than direct poisoning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
CityLearn v3: A Configurable Simulation and Evaluation Framework for Realistic Control Studies of Renewable Energy Communities
Tiago Fonseca, Luis Lino Ferreira, Armando Sousa et al. (+2 more)
Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies often simplify changing participation, equipment availability, service deadlines and data quality, so lower cost or peak demand can conceal missed services or infeasible power requests. This paper presents CityLearn v3, a configurable simulation and evaluation framework for REC control studies under these conditions. It represents changing members and assets, flexible-load deadlines, demand-response requests, local energy sharing, and data or equipment failures within one simulation environment. Building and phase power limits constrain controllable requests, while a declared timestep preserves consistent power-to-energy accounting. The framework records controller inputs and distinguishes requested actions from those applied to the simulated equipment. Reference controllers, service- and constraint-aware performance indicators, and trajectory exports support comparisons within and across communities. Software checks and application examples examine service delivery, electrical constraints, settlement and changing scenarios; a synthetic high-frequency trace replay illustrates how aggregation can conceal short peaks without changing annual energy. Together, these records allow aggregate performance to be interpreted alongside service failures, action reductions and participant-level outcomes.
Read the full abstract ▾
All authors Tiago Fonseca, Luis Lino Ferreira, Armando Sousa, Ava Mohammadi, Zoltan Nagy
Artificial Intelligence · Cross-listed from cs.SE
GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions
Xinyu Che, Yunfei Ge, Shihao Li et al. (+9 more)
Coding
agents can modify and test code across large software projects. Game development is a domain where
agents must implement gameplay rules. A game can end in a valid state even after violating its rules during the run. Current game-development
benchmarks replay fixed examples, score
videos, or ask another model to judge the result. However, no existing
benchmark checks game rules throughout execution across varied evaluator-selected scenarios while ensuring exactly reproducible verdicts. We introduce GameLogicBench, a
benchmark of 72 gameplay-logic tasks in Godot projects. An automated evaluator checks each game's rules at every simulation tick. Across 403 hand-designed scenarios, seeded parameter variations produce 1,451 test cases. To ensure that the evaluator measures behavior rather than implementation choice, it must accept different correct implementations for each task while rejecting mutants, implementations with one required capability removed. The tasks span isolated mechanics, multi-system interactions, and repository-scale features. Across 20 combinations of
language models and scaffolds, the best observed run solves 52.78% of tasks. Under Claude Code, all twelve models solve fewer tasks as task scope expands from isolated mechanics, through interacting systems, to repository-scale features.
Agents inspect code more often and make more tool calls on repository-scale tasks than on isolated-mechanic tasks. Most unsuccessful submissions are runnable, but implement some required game behavior incorrectly. We compared versions of our
benchmark evaluator built with and without validation using mutants. Without this validation, incorrect
agent submissions passed. A separate analysis finds
agents copying code from public repositories when network access is open. Reliable evaluation thus depends both on what the tests reject and on what external code
agents can access.
Read the full abstract ▾
All authors Xinyu Che, Yunfei Ge, Shihao Li, Yanchen Liu, Hang Yan, Xinping Lei, Yanghai Wang, Zixuan Dong, Yifan Yao, Qianqian Xie, Letian Zhu, Jiaheng Liu
Artificial Intelligence · Cross-listed from cs.LG
On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub et al. (+4 more)
On-policy self-
distillation provides dense,
token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution back into the model. However, privileged information can change not only what the teacher knows, but also how it behaves, entangling correctness-relevant learning signals with unintended behavioral shifts. We study this effect in
reasoning tasks by contrasting attractive self-
distillation, which moves the model toward a privileged teacher, with repulsive self-
distillation, which moves it away from a privileged teacher. We find that both objectives can induce strong and opposing behavioral shifts: attraction suppresses exploratory
reasoning and promotes shorter, more confident responses, whereas repulsion increases response length, can trigger unintended switches into a model's latent thinking mode, and ultimately becomes unstable. Motivated by these observations, we study contrastive self-
distillation, which combines attraction toward a correct-solution-conditioned teacher with repulsion from an incorrect-solution-conditioned teacher. In contrast to prior work that combines such
distillation signals with a GRPO objective, we isolate the self-
distillation objective and study its behavior on its own. We find that the shared behavioral shifts of the two teachers largely cancel, leaving a
token-level signal that more directly reflects correctness. Across non-thinking, instruct-only, and already-thinking models, this contrastive objective improves
reasoning performance while maintaining stable response lengths.
Read the full abstract ▾
All authors Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub, Frederike Lübeck, Jonas Hübotter, Thomas Kleine Buening, Andreas Krause
Artificial Intelligence · Cross-listed from cs.LG
OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios
Yewen Li, Peng Jiang, Yitian Li et al. (+4 more)
Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has evolved from rule-based controllers to reinforcement learning and generative methods such as Decision
Transformer (DT). Yet these methods increasingly mismatch the prevailing optimized cost-per-X (oCPX) paradigm, which spans heterogeneous scenarios (e.g., registration, purchase), each served by a separate model, leading to fragmented pipelines and underexploring cross-scenario modeling. Inspired by foundation models like LLMs, unifying these oCPX scenarios into one model raises three challenges: multi-objective control, scalable capacity under strict latency, and safe offline policy improvement. We present OneBid, a unified auto-bidding foundation model that learns a reusable backbone from heterogeneous oCPX logs and adapts it to scenario-specific deployments via offline post-training. Building on DT, OneBid extends single Return-to-Go conditioning to two atomic signals, Return-to-Go for conversion value and Cost-to-Go for cost ratio, plus value-aware regularization on next-action prediction. To absorb distributional heterogeneity, we design a sequence-level Mixture-of-Experts architecture, where shared experts encode cross-scenario knowledge and sparsely-routed experts capture scenario-specific patterns at low latency, yielding consistent scaling with model size and data. During post-training, we align the backbone with scenario preferences via Critic-guided Relative Offline Policy optimization (CROP): a learned critic scores candidate actions group-relatively, avoiding the unsafe online exploration of GRPO-style fine-tuning while constraining policy shift to reduce OOD risk. Validated via online A/B tests and fully deployed at Kuaishou, OneBid delivers an overall +2.2% ADVV gain on oCPX Ads, peaking at +13.1% in the ROAS scenario.
Read the full abstract ▾
All authors Yewen Li, Peng Jiang, Yitian Li, Pengfei Lv, Xialong Liu, Peng Jiang, Qingpeng Cai
Artificial Intelligence
Dual-Interest Sequential Product Recommendation With Multi-Granular SSM
Shuiying Liao and P. Y. Mok
Sequential recommendation aims to predict the next item a user will interact with based on their historical behavior. Advances in
Transformers have significantly improved sequential recommendation but are still limited by cost efficiency. Although State Space Models (SSMs) have recently enabled efficient long-range modeling, most existing methods encode each item with a single static contextual role, overlooking the phenomenon of item polysemy. In fact, the same item often plays different semantic roles depending on user context, and existing methods are limited in capturing dynamic behavior across different temporal granularities. In this work, we propose DSRec, a novel dual-interest cross-SSM model that explicitly disentangles item roles across long-term and short-term semantic context. Sequential items are encoded into long-term interest
embeddings that capture stable preferences via historical aggregation, and a short-term interest branch that emphasizes local session intent modulated by inter-click time intervals. These interest
embeddings are processed through distinct SSM encoders: a full-sequence Mamba for long-term modeling, and a time-modulated SSM that dynamically adjusts state
evolution based on temporal gaps. To enable effective cross-granularity
alignment, we adopt a residual cross-fusion mechanism that exchanges contextual information between the two branches while preserving semantic independence. Experiments on public
benchmarks demonstrate that DSRec outperforms other state-of-the-art methods.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration
Changbeen Kim, Junwon Chang, Kipyo Kim et al. (+3 more)
While
Video Large
Language Models (
Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained
video understanding remains challenging. Existing
benchmarks often rely on question answering or ground-truth caption matching, where models may succeed through superficial cues and incomplete annotations. To this end, we introduce VidOmni-Bench, a
benchmark that requires models to verify whether each event in dense
video captions is supported by the
video. VidOmni-Bench consists of 500
videos spanning five complexity types and diverse durations from 4 seconds to 90 minutes. After collecting
videos along these axes, we use diverse
Video-LLMs to generate dense captions and obtain human-verified sentence-level labels, where sentences containing incorrect events serve as hard negatives for evaluation. Our experiments on VidOmni-Bench reveal three key findings: (i)
Video-LLMs frequently generate hallucinated descriptions in dense
video captioning; (ii) they also struggle as verifiers, failing to reliably detect plausible but incorrect event descriptions; and (iii) model weaknesses vary across
video complexity and duration, revealing diverse, model-specific bottlenecks in current
Video-LLMs.
Read the full abstract ▾
All authors Changbeen Kim, Junwon Chang, Kipyo Kim, Risa Shinoda, Kuniaki Saito, Donghyun Kim
Artificial Intelligence
Learning-to-Optimize as the Missing Architectural Layer of AI-Native Networks
Giambattista Amati, Federica Mangiatordi, Pierpaolo Salvo et al. (+2 more)
Artificial Intelligence (AI) is becoming a fundamental design principle of future AI-native communication networks, enabling autonomous resource management, adaptive control, and zero-touch network operation. While current AI-native architectures increasingly embed intelligence across network functions, they provide little guidance on how optimisation knowledge should be systematically generated, transferred, and exploited by AI models. This paper argues that the Learning-to-Optimize (L2O) represents the missing architectural layer between optimisation and AI-native intelligence. Rather than viewing optimisation merely as an online decision engine, the proposed paradigm redefines optimisation
algorithms as offline knowledge generators that produce high-quality supervisory information for neural surrogate models. The resulting models inherit optimisation expertise while enabling low-latency runtime inference suitable for dynamic network environments. A generic four-stage L2O workflow is introduced, comprising optimisation, knowledge generation, surrogate learning, and runtime inference. Unlike existing Learning-to-Optimize approaches, which primarily focus on
algorithm acceleration, the proposed framework establishes L2O as an architectural abstraction applicable across heterogeneous communication and computing systems. The proposed paradigm is illustrated by an NR-V2X relay-selection problem, in which optimisation-generated solutions from a Mixed-Integer Linear Programming (MILP) solver are used to train a Graph Neural Network that can reproduce near-optimal decisions in real time. The presented perspective positions Learning-to-Optimize as a key architectural enabler for future AI-native networks.
Read the full abstract ▾
All authors Giambattista Amati, Federica Mangiatordi, Pierpaolo Salvo, Emiliano Pallotti, Simone Angelini
Artificial Intelligence · Cross-listed from cs.RO
2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation
Muneeb A. Khan, Woojin Kim, Shinwoo Kim et al. (+3 more)
This report describes our 2nd place solution to the HANDS 2026 workshop challenge (Dexterous Grasp Motion track) in conjunction with ECCV 2026. In this challenge, we address grasp motion generation for the 12-DoF LinkerHand O6, aiming to produce physically plausible reach-and-lift trajectories for unseen objects from randomized initial hand poses in simulation. This task is particularly challenging because each grasp requires a per-step policy to make approximately $70$ twelve-dimensional decisions, with errors accumulating over time, while test objects and physical dynamics may differ from those encountered during training. To address these challenges, we propose editing a single successful GraspM3 demonstration instead of generating the motion step by step: a policy observes the object once and outputs a 12-D warp of the demonstration, which is then replayed open-loop. Moreover, we train the warp policy with one-step PPO over all $4{,}824$ training objects in parallel. As a result, our method achieved success rates of $94.61\%$ on the easy track, the highest of all submissions, and $57.18\%$ on the hard track of the private test set.
Read the full abstract ▾
All authors Muneeb A. Khan, Woojin Kim, Shinwoo Kim, Muhammad Munsif, Binod Bhattarai, Seungryul Baek
Artificial Intelligence
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella et al. (+1 more)
When
language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural
language. How much tree-structured compositional content survives this bottleneck? We propose a round-trip protocol that answers this question empirically for tree-structured expressions. A generator converts a procedurally generated arithmetic expression into a word problem, a separate extractor recovers the expression from the word problem alone, and symbolic equivalence provides an exact oracle. Evaluating all pairwise combinations of sixteen models yields a communication
matrix whose marginals separate generation quality from extraction quality. Three main findings emerge. First, the channel is lossy and asymmetric: swapping which model generates and which extracts shifts accuracy by up to 60.4 points, and the best pair reaches 92.9% by combining different models on each end rather than the same model on both. Second, at least 73.6% of round-trip failures originate at generation, and difficulty is driven by tree structure (operator count, depth, right-branching) rather than model family. Third, the channel is trainable: ~3600 fine-tuning examples that share the evaluation's operators and tree shapes lift every open-weight model above untrained Gemini-3.1-Pro, an upper bound under matched semantics. A disjoint-domain regime with new operators and vocabulary also raises every open-weight model, confirming the gain is not an artifact of matched semantics, though a gap to the frontier remains. Together these results identify tree-structured expression serialization as a primary limiting factor when models communicate hierarchical structure through natural
language.
Read the full abstract ▾
All authors Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella, Samy Bengio
Artificial Intelligence
PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design
Zicheng Zhao, Dongyin Chen, Rui Xu et al. (+1 more)
Multimodal large
language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whether an engineering design will work when executed. Existing
benchmarks assess spatial
reasoning, structural validity, or physics-grounded construction, but they do not determine whether MLLMs can synthesize complete load-bearing structures and repair them after simulator execution exposes a failure. We introduce PolyBridgeBench, an executable
benchmark for
multimodal bridge design. A model receives a visual scene and structured engineering constraints and generates a complete node–member–material
topology. Deterministic legality checks gate execution in a native dynamic physics simulation. Following an execution failure, the
benchmark returns temporal visual evidence from the failed rollout and evaluates repair under a fixed interaction budget. Separate measurements of deterministic validity, dynamic functional success, and post-failure recovery identify the stage at which design fails. Experiments with six representative MLLMs across 189 levels expose a substantial gap between deterministic validity and dynamic success, pronounced sensitivity to material budgets, and limited post-failure recovery under the primary strict-budget setting.
Read the full abstract ▾
All authors Zicheng Zhao, Dongyin Chen, Rui Xu, Yinghui Xu
Artificial Intelligence
LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers
Jingyu Hu, Shu Yang, Weiru Liu et al. (+1 more)
Chain-of-Thought (CoT)
reasoning has been shown to improve the performance of large
language models (LLMs), yet existing optimization methods largely rely on outcome-based feedback, leaving the logical validity of intermediate
reasoning steps largely unverified. To address the gap whereby LLMs arrive at correct final answers through logically flawed intermediate
reasoning chains, we propose LogicTrack, a neuro-symbolic framework that audits
reasoning trajectories by auto-formalizing each
reasoning step into symbolic representations and verifying it with automated
theorem provers. LogicTrack introduces Solver-Based Backtracking Reward (SBR), a step-wise scoring mechanism that quantifies logical soundness and guides backtracking tree search at inference time. We further extend LogicTrack to construct supervised fine-tuning (SFT) data with backtracking traces from its trajectories, enabling fine-tuned models to internalize step-wise
auditing as an intrinsic capability. Extensive experiments across 8
reasoning benchmarks and 7 LLMs demonstrate that LogicTrack effectively improves both the verifiability of
reasoning chains and final answer pass rate, thereby enhancing overall CoT quality and trustworthiness in high-stakes domains.
Read the full abstract ▾
All authors Jingyu Hu, Shu Yang, Weiru Liu, Di Wang
Artificial Intelligence
Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving
Jiaxing Chen, Hengduo Zou, YuKai Qin et al. (+3 more)
Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline, bad and poor candidates constitute 19.74% of the candidate set, while the oracle-best candidate ranks only 33.9th on average. We propose RRDrive, which introduces risk-aware occupancy as a dense, temporally aligned, and trajectory-queryable representation. Its global structure guides high-quality
multimodal generation, while candidate-conditioned risk queries support fine-grained selection. We further construct RiskOcc4D-NAVSIM with automatic risk annotations. RRDrive achieves a selected-trajectory PDMS of 0.951, representing a 1.5% relative improvement over the baseline (0.937), and improves the average candidate PDMS by 7.7%. In challenging scenes, it improves candidate PDMS by 30.2% and increases the Spearman correlation among good candidates by 0.41, from 0.26 to 0.67. To move beyond this oracle setting, we further develop an external RiskOcc predictor, a perception module that estimates risk-aware occupancy directly from sensor inputs. The competitive performance validates the representation's feasibility.
Read the full abstract ▾
All authors Jiaxing Chen, Hengduo Zou, YuKai Qin, Yiren Zhao, Lidong Yu, Bolin Gao
Artificial Intelligence · Cross-listed from cs.CR
HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
Byeongseo Min, Yongwoo Lee, Young-Sik Kim et al. (+1 more)
Homomorphic encryption (HE) has emerged as a promising approach to
privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-based PPML, a client submits an encrypted input to the server, which evaluates models such as large
language models (LLMs) without access to the underlying plaintext. However, we identify a critical security vulnerability in this setting: HE-LLM inference is vulnerable to malicious clients that submit
adversarial prompts, such as jailbreak attacks. The same confidentiality that protects benign clients also prevents the server from inspecting incoming
prompts or generated responses, making
adversarial attempts difficult to detect or block and potentially allowing successful attacks to remain entirely invisible to the server. To address this vulnerability, we propose HE-Guardrail, a framework that evaluates guardrail mechanisms entirely over encrypted data and homomorphically controls whether the target-model response is returned to the client. We instantiate HE-Guardrail with three representative guardrails - Llama Guard, JBShield, and GradSafe. Our results show that HE-Guardrail closely reproduces the decisions of the corresponding plaintext guardrails in the encrypted domain, with distinct security-efficiency-utility trade-offs.
Read the full abstract ▾
All authors Byeongseo Min, Yongwoo Lee, Young-Sik Kim, Yongjune Kim
Artificial Intelligence
Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving
Jiaxing Chen, Hengduo Zou, Yiren Zhao et al. (+1 more)
Conventional end-to-end driving systems model the environment with sparse objects and lane elements. While efficient, this paradigm discards planning-critical information in crowded and occluded scenarios, particularly for unstructured obstacles, ambiguous free space, and complex interactions. We propose risk-aware occupancy, a dense BEV representation that explicitly fuses
geometric occupancy, map-derived traffic constraints, and future dynamic-
agent occupancy as complementary risk signals. Built upon this representation, we develop ROIDrive, an instance-centric end-to-end framework with a dedicated risk-aware occupancy branch. The predicted occupancy is tokenized via sliding-window sampling and injected into planning queries via cross-
attention, while temporal query consistency mitigates unreliable flickering queries. We also contribute RiskOcc4D-nuScenes, a
benchmark derived from nuScenes and Occ3D-nuScenes with four automated annotation pipelines for multi-dimensional risk supervision. Experiments on representative occupancy architectures verify the learnability and transferability of our representation. Integrated with GenAD, it reduces collision rates by 35.0% (UniAD metric) and 52.9% (ST-P3 metric), confirming the efficacy of the proposed representation modality.
Read the full abstract ▾
All authors Jiaxing Chen, Hengduo Zou, Yiren Zhao, Bolin Gao
Artificial Intelligence · Cross-listed from eess.AS
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
Haolin He, Yunfei Chu, Qi Chen et al. (+15 more)
We define OmniVChat (Omni
Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and
video from a user and return text. The user's query is embedded in the audio and
video, without a separate text question, external captioning, or
speech recognition. Direct audio-visual input reduces external latency and computation while preserving perceptual cues. However, research on OmniVChat faces two constraints: data availability and evaluation. Recordings of people using their own devices are scarce. Furthermore, good replies often depend on
multimodal context and can be phrased in many ways, making keyword matching unreliable for evaluation. Recent progress in
agent systems and
video generation makes generation for comprehension viable, which means using synthesized dialogues for training and evaluation. Therefore, we present OmniVChat-Studio, a multi-
agent data engine for synthesizing single- and multi-turn audio-visual dialogues. We use synthesized dialogues to build OmniVChat-Bench, an evaluation
benchmark that evaluates omni models' basic dialogue abilities across five ability categories. Replies are judged by a large
language model based on explicit scoring criteria. We also present OmniVChat-RL, a reinforcement learning reward design that jointly targets reply correctness, efficiency, and style in OmniVChat. Training Qwen3-Omni-Instruct with OmniVChat-RL on synthesized dialogues improves its performance on both OmniVChat-Bench and the human-recorded OmniVChat-Bench-Human. These gains validate the reward design and show transfer to real-world dialogues in training and evaluation.
Read the full abstract ▾
All authors Haolin He, Yunfei Chu, Qi Chen, Wen Huang, Yuan Feng, Muzhi Zhu, Zheqi Dai, Haoning Xu, Dongchao Yang, Chunyat Wu, Zining Liang, Zhengxi Liu, Xiquan Li, Xie Chen, Xize Cheng, Qize Yang, Jin Xu, Qiuqiang Kong
Artificial Intelligence · Cross-listed from cs.RO
AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining
Di Wu, Dongchen Zheng, Junhe Sheng et al. (+8 more)
Embodied foundation models are constrained by the limited scale and diversity of
robot demonstrations, motivating the use of large-scale
egocentric human interaction data. However, how to effectively incorporate such data into
embodied-model pre-training remains unclear because of substantial embodiment and action-space gaps between humans and
robots. We present AtomEgo, a systematic study of ego–
robot co-training supported by a curated corpus of approximately 2,659 hours and a scalable data processing pipeline. Across
vision–
language–action and world–action model architectures, we investigate three representative paradigms: joint co-training with domain-specific action heads, progressive ego-to-
robot transfer through embodiment
alignment, and joint
video–action modeling. We evaluate these paradigms through multi-task real-
robot experiments and
language-conditioned cross-embodiment representation analysis. Our results reveal a simple principle: Data Scale *
Alignment Quality –> Capability Gain;
egocentric data can improve generalization, but their value depends on how effectively they are aligned and utilized. This principle can provide practical guidance for scalable ego–
robot pre-training.
Read the full abstract ▾
All authors Di Wu, Dongchen Zheng, Junhe Sheng, Zhongxing Wei, Songxin Zhang, Zejian Xie, Xiaoquan Sun, Junyang Zheng, Zhuoyang Song, Jiaxing Zhang, Jiayu Chen
Artificial Intelligence · Cross-listed from cs.IT
Interference-Driven Clustered Optimisation for FM Spectrum Coordination
Federica Mangiatordi and Emiliano Pallotti
Cross-border FM spectrum coordination involves protecting foreign broadcasting services while preserving domestic coverage, amid increasingly large
radio-planning
datasets containing thousands of transmitters and millions of transmitter-pixel relationships. In such scenarios, conventional optimisation approaches become computationally demanding due to the high dimensionality of the associated power-control problem. This paper proposes an interference-driven clustered optimisation framework for large-scale FM spectrum coordination. The proposed method exploits the observation that violations of foreign-service protection are typically dominated by a limited subset of transmitters. Protected services are therefore analysed to identify dominant interferers and quantify their impact on interference. These relationships are represented through an interference graph from which optimisation-oriented transmitter clusters are extracted. The clusters decompose the global power-control problem into smaller optimisation tasks solved with clustered simulated annealing, followed by a global refinement that captures residual inter-cluster interactions. Coverage and interference are evaluated using frequency-dependent protection criteria and a dynamic strongest-service assignment model. To enable operational-scale planning, the framework uses sparse
matrices and GPU-accelerated computations. Tests on realistic cross-border FM coordination scenarios show that the clustering strategy greatly reduces optimisation complexity and runtime while maintaining foreign-service protection and domestic coverage. The method also yields an interpretable ranking of transmitters that contribute most to harmful interference, supporting optimisation and spectrum planning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction
Jingke Zhou, Chenhang Ma, Zhizhou Zhong et al. (+6 more)
We propose LoG-VGGT, a
memory-efficient framework for long-sequence 3D reconstruction that balances local temporal modeling with global camera consistency. Instead of relying on full global
attention, our method introduces cross-window
attention at a small subset of
transformer blocks, enabling effective information propagation across adjacent temporal windows while keeping
memory usage bounded. To mitigate long-term pose drift, we further design a global camera consistency refinement module, where camera
tokens interact with compact register
tokens via cross-
attention to enforce scene-level constraints across the entire sequence. This design enables joint optimization of camera representations and significantly improves long-horizon pose stability without incurring the high cost of sequence-wide
attention. Extensive experiments demonstrate that LoG-VGGT achieves improved depth accuracy and robust camera pose estimation across multiple long-sequence
benchmarks, while delivering competitive streaming reconstruction performance.
Read the full abstract ▾
All authors Jingke Zhou, Chenhang Ma, Zhizhou Zhong, Mingkai Liu, Zhuang Zhou, Yicheng ji, Binghua Su, Bo Cai, Xianliang Huang
Artificial Intelligence
GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
Kaichen Zhang, Yuzhong Hong, Junwei Bao et al. (+4 more)
Post-training plays a pivotal role in enhancing the
reasoning capabilities and task-specific expertise of large
language models (LLMs). Despite recent advances in post-training methods, such as Group Relative Policy Optimization (GRPO), their practical deployment remains impeded by training instability arising from the reliance on importance sampling. We introduce Group Variance Policy Optimization (GVPO), a novel post-training method that integrates the analytical solution of KL-constrained reward maximization into its gradient weighting scheme. This formulation provides an intuitive interpretation: GVPO's gradient corresponds to the mean squared error between the central distance of implicit rewards and that of actual rewards. GVPO offers two key advantages: (1) it guarantees a unique optimal solution, exactly to the KL-constrained reward maximization objective, and (2) it enables flexible sampling distributions without requiring importance sampling. Beyond general post-training, we show that GVPO naturally extends to on-policy
distillation (OPD). Furthermore, GVPO enables the optimization of a broad family of extended OPD objectives, providing a principled foundation for diverse objective design. By unifying theoretical guarantees with practical adaptability, GVPO establishes a new paradigm for reliable and versatile LLM post-training and on-policy
distillation.
Read the full abstract ▾
All authors Kaichen Zhang, Yuzhong Hong, Junwei Bao, Hongfei Jiang, Yang Song, Dingqian Hong, Hui Xiong
Artificial Intelligence
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
Siyuan Liu, Fan Yu, Dongyu Ru et al. (+5 more)
Online
agent deployments accumulate execution trajectories at massive scale and behavioral diversity, for which predefined annotation criteria hardly exist. Extracting useful evidence therefore demands costly manual annotation or verifier signals that fail to scale, leaving valuable evidence buried among redundant, incomplete, and failed executions. This raises a question: without post-execution rewards or correctness labels, how can reusable experience be distilled from the trajectories themselves? To address this challenge, we introduce DENSE (Distilling Evidence from Nested Subtask Executions), which organizes trajectory-derived evidence into nested shortcut trees. By consolidating redundant attempts, identifying resolved subtasks, and retaining useful steps alongside outstanding requirements, DENSE transforms noisy execution traces into structured and reusable task-solving feedback. To evaluate whether such feedback helps
agents retry the same task, we design REFIT, which measures success-rate changes between the initial attempt and feedback-guided retries. Among feedback methods without external outcome supervision, DENSE achieves the highest strict pass rate across four
agent models on Terminal-Bench 2.1, improving over initial attempts by 7.12-21.81 percentage points with 19.0-43.6% fewer
agent tokens on retries. In addition, on hard tasks DENSE consistently outperforms self-reflection in cumulative pass rate across multiple feedback iterations on all four models, demonstrating its strong potential for continual
agent self-improvement.
Read the full abstract ▾
All authors Siyuan Liu, Fan Yu, Dongyu Ru, Yizhu Liu, Yifan Yang, Xuezhi Cao, Xunliang Cai, Yixin Cao