Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Monday 22 June

Artificial Intelligence · Cross-listed from eess.SP

Integrated Sensing and Communications for Real-time Avatar Control in XR over 5G

Nabeel Nisar Bhat, Javad Sameri, Rreze Halili et al. (+3 more)

Extended Reality (XR) presents a challenging use case for 5G and 6G networks, requiring high data-rates and lowlatency communication to deliver a truly immersive experience. Moreover, in order to seamlessly translate physical actions to the virtual world, accurate gesture recognition and pose estimation are required. Current XR interaction solutions based on handheld controllers and cameras cannot easily capture full-body poses, inhibit the free use of hands, and require good visibility and a clear line of sight. In this work, we propose a multimodal sensing architecture for XR that combines 5G MillimeterWave (mmWave) Integrated sensing and communication (ISAC) and surface electromyography (sEMG) signals. 5G mmWave ISAC cannot only be used to deliver content wirelessly to the Head-mounted display (HMD), but also the same communication signals can be used to derive coarse body-level gestures and poses of the user, to support real-time avatar control. For fine-grained finger-level gestures, our architecture leverages lightweight sEMG sensors that capture forearm muscle activity. To illustrate the need of both modalities, we present evaluations of both sensing technologies. At the body level (5G), our architecture relies on power-per-beam-pair (PPBP), which can be computed from standard beam management or beam sweeping procedures of the 5G NR standard. PPBP-based sensing achieves 82.2$\pm$5.9% average accuracy when evaluated on users not seen during training. For fine-grained finger-level interactions, we show that surface electromyography (sEMG) carries strong discriminative information achieving consistent promising performance across different movement settings. Thus, combining the two modalities enables multi-scale gesture recognition, at the body level via existing 5G signals and finger level via lightweight sEMG sensors, forming a complete XR framework.
Read the full abstract

All authors Nabeel Nisar Bhat, Javad Sameri, Rreze Halili, Rafael Berkvens, Maria Torres Vega, Jeroen Famaey

Artificial Intelligence · Cross-listed from cs.CR

Cryptographic certificates of validity for trustworthy AI

Murdoch J. Gabbay

We propose cryptographic certificates of validity for agentic AI systems. The core idea is to formally specify a correctness or policy condition as a logical predicate, compile this predicate to a witness-checking problem over polynomial constraints, and use a succinct cryptographic proof system (and optionally zero-knowledge) to certify that the condition holds. This offers a middle ground between formal verification of source code, and cryptographic authentication. An agent's action can be accompanied by an independently checkable proof that it satisfies an agreed formal policy, without requiring the verifier to trust the agent or to re-execute computation. We outline the approach at a high level, give the core mathematical translation, relate the proposal to proof-carrying code, zkVMs, formal methods, and agent governance, and note the specification, auditing, and deployment questions that a full implementation must answer.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.MA

Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification

Zhiyuan Ji, Xinyu Chen, Ziqi Dai et al. (+3 more)

Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance. Although often treated as culturally specific, its mechanistic basis remains under-operationalized, and prior LLM-based simulations have mainly addressed short-term coordination rather than long-horizon social structure. We propose CAREB-MAS, a multi-agent framework grounded in Affect Control Theory, Social Identity Theory, and Durkheimian collective affect. Agents reason through an emotion-ethics-belief chain and maintain dynamically evolving egocentric identities, while the macro environment specifies only individual production, preference-based allocation, and minimal interaction protocols. Across long-horizon simulations, agents spontaneously reproduce five core Differential Order phenomena: stable labor specialization, guanxi-based economic ethics, relational decay of cooperation, emergent relational authority, and clan-based center-periphery stratification. These patterns shift with production structure from kin-centered integration toward greater functional interdependence. Extensive experiment results support interpreting Differential Order as a structure-sensitive emergent outcome of general social mechanisms, with LLM-based multi-agent simulation providing an interdisciplinary framework for studying social structure and change.
Read the full abstract

All authors Zhiyuan Ji, Xinyu Chen, Ziqi Dai, Shiyun Tang, Chunyu Wei, Yueguo Chen

Artificial Intelligence · Cross-listed from cs.CV

Listening makes Vision Clear for VLMs

Yiyang Chen, Yixin Tan and Binrui Shen

Recent work typically assesses vision–language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these distortions and provide consistency evaluation for large VLMs, we adopt prompt-side semantics and propose Prompt-Vision Token Activation Map (PV-TAM). PV-TAM further incorporates a filter to remove systematic bias induced by modality boundary markers. Unlike traditional methods that evaluate overlap solely through masks while ignoring activation intensity, our metrics leverage the peak distribution of attention to measure the alignment between prompts and visual regions. In experiments, PV-TAM consistently improves both attention-based and IoU-style localization metrics over answer-side baselines on various datasets.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.SD

Neuromorphic Speech Enhancement with Dual-Branch Spiking Neural Networks

Taiyu Meng, Wenbin Jiang, Haoyi Zhang et al. (+2 more)

Spiking neural network (SNN)-based neuromorphic speech enhancement has emerged as a promising paradigm due to its energy efficiency, yet it still underperforms classical artificial neural network (ANN)-based approaches owing to binary activations and the lack of well-designed network architectures. To overcome this limitation, we propose a novel dual-branch spiking neural network architecture equipped with a gated spiking unit (GSU), termed GSU-DBNet. Specifically, GSU-DBNet simultaneously models the speech magnitude spectrum and complex spectrum, predicting the corresponding magnitude and complex spectral masks. Meanwhile, a dual-path GSU module is adopted to exploit temporal and frequency information for enhanced spatiotemporal feature representation. Experiments on a popular benchmark dataset show that GSU-DBNet achieves a PESQ score of 3.04 with only 394K parameters, outperforming existing SNN-based methods while using only 4.5%–10.6% of the parameters of representative ANN-based models.
Read the full abstract

All authors Taiyu Meng, Wenbin Jiang, Haoyi Zhang, Yuhan Zhou, Haibing Yin

Artificial Intelligence · Cross-listed from cs.RO

Engineering Reliable Autonomous Systems: Challenges and Solutions

Marie Farrell, Matt Luckcuck, Angelo Ferrando et al. (+28 more)

Engineering reliable autonomous systems is an important and growing topic in computer science. As autonomous systems become more prevalent, easy-to-use techniques for building them reliably are increasingly important. This workshop report captures and expands on the discussions at the Lorentz Center Workshop "Engineering Reliable Autonomous Systems" (ERAS), held from 10 to 14 June 2024. The workshop was co-organised by the organisers of the Workshop on Formal Methods for Autonomous Systems (FMAS) and the Workshop on Agents and Robots for reliable Engineered Autonomy (AREA). It brought together members of the FMAS and AREA communities, industry practitioners, and representatives from sectors where autonomous systems pose distinctive engineering challenges. The workshop focused on three main research topics: techniques for verification and validation of autonomous systems; engineering real-world autonomous systems; and software architectures for safe autonomous systems. Its main outcome is a catalogue of challenges in these areas and, most importantly, a pathway to solutions. Some challenges can already be tackled by techniques that are well known in academia but have not yet become regularly used in practice. Other challenges remain unresolved and require further research. This roadmap is intended to support future research and industrial collaboration.
Read the full abstract

All authors Marie Farrell, Matt Luckcuck, Angelo Ferrando, Rafael C. Cardoso, Natasha Alechina, Marco Autili, Diana Benjumea Hernandez, Luciana Brasil Rebelo dos Santos, Daniela Briola, Ana Cavalcanti, Christian Colombo, Louise A. Dennis, Clare Dixon, Michael Fisher, Mario Gleirscher, Taylor Johnson, Charles Lesire, Livia Lestingi, Sven Linker, Brian Logan, Colin Paterson, Fabio Papacchini, Patrizio Pelliccione, Pedro Ribeiro, Maike Schwammberger, Silvia Lizeth Tapia Tarifa, Hazel Taylor, Jim Woodcock, Mengwei Xu, Yi Yang, Huan Zhang

Artificial Intelligence · Cross-listed from cs.AR

VeriPilot: An LLM-Powered Verilog Debugging Framework

Yihan Wang, Cheng Liu, Jiazheng Zhang et al. (+4 more)

Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enabled automated debugging; however, most existing approaches rely solely on test outputs and compiler feedback in an end-to-end manner, limiting their effectiveness on complex bugs. A key challenge is that the root cause of an error may be far removed from its observable outputs, making it difficult for LLMs to trace long dependency chains in code. This challenge is further exacerbated in large codebases, where long context lengths hinder efficient reasoning. To address these limitations, we propose VeriPilot, an LLM-powered debugging framework that leverages golden reference models to enable fine-grained bug localization and repair. VeriPilot goes beyond output-level comparison by aligning internal variable semantics between the Verilog design and its corresponding golden model through LLM-based analysis. It then performs step-by-step signal tracing using Control-Data-Flow Graphs (CDFGs) derived from static analysis, identifying a minimal set of suspicious code regions along with their correct counterparts from the golden model. These structured insights are subsequently provided to the LLM to guide reasoning and automated code repair. Experimental results on the Comprehensive Verilog Design Problems (CVDP) benchmark from NVIDIA demonstrate that VeriPilot improves the repair success rate of GPT-4o from 54.3% to 85.71%, significantly enhancing both bug localization accuracy and repair effectiveness for complex Verilog designs. The source code and benchmark are publicly available at Github https://github.com/YihanWn/VeriPilot.git.
Read the full abstract

All authors Yihan Wang, Cheng Liu, Jiazheng Zhang, Lei Zhang, Long Cheng, Xiaowei Li, Huawei Li

Artificial Intelligence · Cross-listed from cs.LG

Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios

Xiran Wang, Jian Zhang, Lei Qi et al. (+2 more)

Domain generalization learns from multiple source domains to generalize to unseen target domains. However, it often neglects the realistic case of label mismatch between source and target. Open set domain generalization is then proposed to recognize unseen classes in unseen domains. A simple approach trains one-vs-all classifiers to separate each class and detect outliers as unknown. Yet, the imbalance between few positive samples and many negative samples skews the decision boundary towards the positive ones, leading the model to over-reject out-of-distribution data, even from known classes in unseen domains. In this paper, we propose a novel meta-learning stategy called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers implicit gradient matching towards inter-domain and inter-class task splits simultaneously to find optimal boundaries balanced for both domains and classes. Experimental results show that MEDIC not only outperforms prior methods in open set scenarios, but also maintains competitive close set generalization ability.
Read the full abstract

All authors Xiran Wang, Jian Zhang, Lei Qi, Yang Gao, Yinghuan Shi

Artificial Intelligence · Cross-listed from cs.LG

Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery

Runzhe Liu, Zihao Wang, Wenbo Yang et al. (+1 more)

Extracting interpretable governing equations from sparse, noisy chemical time-series data remains difficult because discrete reaction topology and continuous kinetic parameters are tightly coupled. We present PC-MCMC-CIGP, a reproducible gray-box workflow that combines spike-and-slab topology sampling, hard conservation and thermodynamic screening, and a Chemical-Informed Gaussian Process (CIGP) residual model for parameter calibration and experimental design. The methodological contribution is not a new MCMC or GP family in isolation; rather, it is the integration of these components into a physically constrained workflow with explicit uncertainty-aware acquisition choices. On the H2 + Br2 benchmark, the constrained sampler distinguishes elementary radical pathways from deceptive phenomenological fits in our experiments. On styrene epoxidation, the CIGP optimization loop improves final yield by 12.5% over the reported GP-BO baseline. A new 10-seed acquisition study shows that EI, GWU, PC-EI, uncertainty sampling, discrepancy hunting, and random search have different trade-offs: PC-EI substantially reduces low-yield BO suggestions, while EI-style criteria give the strongest final-yield performance.
Read the full abstract

All authors Runzhe Liu, Zihao Wang, Wenbo Yang, Shengyang Tao

Artificial Intelligence · Cross-listed from cs.RO

CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation

Sikai Li, Shuning Li, Zhenyu Wei et al. (+3 more)

Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It also commonly relies on low degree-of-freedom (DoF) end effectors that behave like an open-close grasp primitive. We introduce CoorDex, a learning pipeline that converts high-dimensional body and dexterous hand control into coordinated latent residual control, enabling high-DoF dexterous loco-manipulation on the move. Starting from simulated whole-body and hand demonstrations, CoorDex trains privileged motion tracking teachers for the humanoid body and dexterous hand, distills them into proprioception-conditioned latent priors, and uses the frozen priors as the action space for downstream residual reinforcement learning. A coordinated latent residual policy composes these priors through shared task context and separate body-hand residual heads, preserving natural whole-body motion while improving finger-level contact reliability. CoorDex enables a Unitree G1 humanoid with a 20-DoF WUJI hand to execute dexterous manipulation while in motion, including non-stop bottle grasping and carrying, fridge door opening on the move, and cube pick-and-turn. Ablations on the walk-grasp-carry task show that joint-space PPO, joint-space hand control, and monolithic latent prediction all fail under the same reward budget, while the latent-prior interface and coordinated residual structure make high-dimensional contact-rich loco-manipulation trainable. Project Page: https://skevinci.github.io/coordex/
Read the full abstract

All authors Sikai Li, Shuning Li, Zhenyu Wei, Yunchao Yao, Chenran Li, Mingyu Ding

Artificial Intelligence · Cross-listed from cs.CV

Semantic Browsing: Controllable Diversity for Image Generation

Sara Dorfman, Maya Vishnevsky, Omer Dahary et al. (+2 more)

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rather than meaningful design choices. This motivates a new variant of the diversity task where structure is enforced on the generated samples. We introduce a method for controlled diversity that enables Semantic Browsing, where users can navigate structured image galleries and experience creative exploration through a systematic traversal of meaningful, interpretable axes of variation. Achieving this level of semantic control requires a deep understanding of the scene. We exploit the fact that recent text-to-image models are trained on elaborated captions, effectively decoupling semantic decision-making from pixel generation. This enables a paradigm shift: instead of relying on stochastic variation within the text-to-image model, we induce diversity directly at the text level. By leveraging rich textual representations, we allow a Vision Language Model (VLM) to operate on the full scene context. To overcome the generic outputs typical of standard VLMs, we employ an agentic workflow that explicitly enforces structured variation attuned to the original prompt. We demonstrate that our method produces diverse and navigable design spaces where every variation corresponds to a specific, user-understandable semantic decision.
Read the full abstract

All authors Sara Dorfman, Maya Vishnevsky, Omer Dahary, Or Patashnik, Daniel Cohen-Or

Artificial Intelligence · Cross-listed from cs.CV

AIR: Adaptive Interleaved Reasoning with Code in MLLMs

Cong Han, Xiaohan Lan, Haibo Qiu et al. (+1 more)

Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large language models (MLLMs) has become a pivotal research frontier. The existing literature focuses primarily on tool-use within vision-perception tasks. However, such approaches typically rely on predefined heuristics for visual manipulation and are inherently incapable of addressing numerical computation problems due to their exclusive focus on visual operations. This paper empowers MLLMs with adaptive interleaved reasoning capabilities through extended reinforcement learning training on code-augmented complex numerical computation tasks. To this end, we propose a comprehensive three-component solution consisting of: a two-stage cold-start data construction pipeline, data filtering strategies for RL dataset curation, and an adaptive tool-invocation strategy leveraging a group-constrained reward function for interleaved reasoning trajectories. Extensive experiments demonstrate that after Reinforcement Learning training with the group-constrained reward function, performance improves by an average of 6.1 percentage points (pp) on evaluation benchmarks. Specifically, the accuracy for interleaved reasoning samples increases by 9.9 pp, and the overall success rate of tool-use exceeds 95%. Our data and code are available at: https://github.com/CongHan0808/AIR.git.
Read the full abstract

All authors Cong Han, Xiaohan Lan, Haibo Qiu, Yujie Zhong

Artificial Intelligence · Cross-listed from cs.LG

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

Dingzhi Yu, Hongyi Tao, Yuanyu Wan et al. (+2 more)

AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostly in finite-variance regimes. This is increasingly unsatisfying, as empirical evidence indicates that stochastic gradient noise in LLM pretraining is typically heavy-tailed. Recent work shows that sign-based optimizers such as Lion and Muon achieve sharp heavy-tailed rates, and that AdaGrad can also converge under heavy-tailed noise. However, no rigorous convergence theory for AdamW has yet been established in this regime. Can AdamW converge under the same heavy-tailed assumptions, or does its second-moment accumulator create a genuine obstruction? We formulate this as an open problem, prove a positive weighted-metric benchmark, and give a corridor lower-bound mechanism showing how denominator memory can hide large gradients.
Read the full abstract

All authors Dingzhi Yu, Hongyi Tao, Yuanyu Wan, Luo Luo, Lijun Zhang

Artificial Intelligence

PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support

Sunil Wanjari, Manish Thakre, Aayushi Asole et al. (+4 more)

Mental health assessment commonly relies on isolated screening instruments or data-driven models that often lack interpretability and multi-dimensional integration. Existing approaches frequently focus on individual indicators such as depression or anxiety while providing limited support for comprehensive and explainable decision-making. To address this limitation, this study proposes PsyBridge, a hybrid intelligent decision-support framework designed for multi-dimensional mental health assessment through the integration of clinically validated screening tools, cognitive evaluation, and personality profiling within a unified architecture. The proposed framework incorporates PHQ-9 and GAD-7 assessments alongside cognitive and behavioural indicators using a modular design and a weighted aggregation mechanism to generate interpretable mental health risk classifications and recommendations. To evaluate the framework, a semi-synthetic dataset consisting of 500 patient profiles representing varying severity levels was constructed based on clinically grounded score distributions. Experimental results demonstrate that PsyBridge achieves an overall accuracy of 0.84, outperforming standalone PHQ-9 and GAD-7 assessments while improving precision, recall, and F1-score. Sensitivity analysis and ablation studies further indicate that integrating cognitive and personality components contributes to more stable classification performance and reduces inconsistencies in moderate-risk prediction. The findings suggest that PsyBridge provides a scalable and interpretable approach for AI-assisted mental health decision support, particularly within digital healthcare and telehealth environments.
Read the full abstract

All authors Sunil Wanjari, Manish Thakre, Aayushi Asole, Sharwari Raut, Kwabena Adu-Duodu, Yinhao Li, Stanly Wilson

Artificial Intelligence

Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

Prateek Agnihotri, Sanchit Jain, Prabhat Agnihotri et al. (+2 more)

This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this task, the objective is to discover a hidden logical rule transforming input binary strings to outputs, then apply it to unseen inputs. Large Language Models (LLMs) notoriously struggle here; traditional methods force them to simulate complex boolean logic and arithmetic, leading to hallucinations. Furthermore, the search space of bitwise operations (combinations of shifts, rotations, and logic gates) suffers from a severe combinatorial explosion. To overcome this computational intractability, we present a novel approach that abandons arithmetic logic entirely in favor of string similarity, structured search, and autonomous error recovery. Our core contributions are: 1. Bases and Truth Table Formulation: We reframe logic-gate deduction into a base-selection task, leveraging string similarity (minimal bit flips) to isolate primitive transformations ("bases") and deduce truth tables without complex arithmetic. 2. Backtracking DFS and Error Recovery: We formalize a search process that tests candidate bases, detects logical collisions across examples, and backtracks upon failure to perform robust error recovery. 3. Bit Tokenization and Interactive Reasoning SFT: We force the tokenizer to encode binary strings as individual single-bit tokens. We use dynamic masking to simulate external oracle feedback, training the model to hypothesize, self-evaluate, and backtrack natively. Evaluated on bit manipulation puzzles, our approach achieved over 96% validation accuracy. This represents the highest performance in this category. These algorithmic and training innovations ultimately earned our team the Best Fine-tuning Method and Best Data/Synthetic Data Method awards in the contest, alongside a 7th Place overall finish on leaderboard.
Read the full abstract

All authors Prateek Agnihotri, Sanchit Jain, Prabhat Agnihotri, Aditya Prasad, Shubham Jain

Artificial Intelligence · Cross-listed from cs.LG

Tapered Language Models

Reza Bayat, Ali Behrouz and Aaron Courville

Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly across depth. This is a default inherited from the original transformer and largely unchanged since, yet a growing body of evidence suggests that layers contribute non-uniformly to the final output, with later layers refining the residual stream rather than transforming it. We ask whether parameter capacity should reflect this asymmetry. Our controlled experiment shows that, under a fixed budget, allocating more capacity to earlier layers and less to later layers improves perplexity over a uniform-width baseline, while the reverse allocation hurts. Building on this result, we introduce Tapered Language Models (TLMs), an architectural principle in which a parameter-bearing component is monotonically tapered across depth under a fixed total budget. MLPs are the natural site for this instantiation: they dominate parameter count across all modern LM families and expose width as a single, clean axis of variation. Across three model scales and four architectures (Transformer, Gated Attention, Hope-attention, and Titans), tapering MLP width via a smooth cosine schedule consistently improves perplexity and downstream benchmark performance over uniform baselines, at no additional parameter or compute cost. These findings establish depth-aware capacity allocation as a simple, architecture-agnostic axis of language model design, a free lever hidden in plain sight.
Read the full abstract

Artificial Intelligence

TailorMind: Towards Preference-Aligned Multimodal Content Generation

Hengji Zhou, Ye Liu, Yufeng Liu et al. (+3 more)

Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly to create. Although multimodal generators can synthesize content on demand, how to translate behavioral traces into generation-ready preferences remains underexplored. We study personalized multimodal content generation: creating user-tailored multimodal content without existing item pools or waiting for matching UGC. We propose TailorMind, linking collaborative preference modeling with controllable multimodal generation. TailorMind enriches sparse user histories via hypergraph collaborative filtering and optimizes textual profiles with ranking-error feedback and textual gradient descent. Retrieval-augmented style control grounds outputs in authentic UGC patterns, while cross-modal cohesion reflection reduces semantic drift. We construct TailorBench, a benchmark from three mainstream platforms evaluated along five dimensions: coherence, novelty, aesthetic, hallucination, profiling. Experiments show that TailorMind achieves competitive or stronger coherence, improves novelty and aesthetic quality over representative generation baselines and ground-truth UGC, demonstrating advantages over retrieving available content or comparable UGC, while achieving up to 29% Recall gains in reranking. Our code is released at: https://github.com/iLearn-Lab/TailorMind.
Read the full abstract

All authors Hengji Zhou, Ye Liu, Yufeng Liu, Si Wu, Lianghao Xia, Liqiang Nie

Artificial Intelligence · Cross-listed from cs.LG

Learning Process Rewards via Success Visitation Matching for Efficient RL

Raymond Tsao, Andrew Wagenmaker and Sergey Levine

In many modern applications of reinforcement learning (RL), the natural reward for a task of interest is inherently sparse: a reward of 0 is given everywhere except when the task is completed, when a reward of +1 is given. Training a policy to maximize such a sparse reward requires solving a challenging credit assignment problem, leading to slow or ineffective RL improvement. We propose a simple approach to transform a sparse outcome reward into a dense process reward. Our approach relies on training a discriminator to distinguish between previous successful and unsuccessful episodes, and using this discriminator to incentivize the RL-learned policy to match the state-action visitations of successful episodes, while avoiding those of unsuccessful episodes. By incentivizing the policy to match the visitations over all states, not just those that correspond to task success, this reward provides dense feedback on whether progress is being made towards task completion, and, we show, provably achieves this without changing the optimal policy. Focusing on finetuning of robotic control policies, we demonstrate that our approach leads to significantly faster RL finetuning performance on both simulated and real-world manipulation tasks, as compared to simply maximizing the sparse outcome reward.
Read the full abstract

Artificial Intelligence

AI Exposure Scores: what they measure, what they miss, and what comes next

Campbell Lund, Thomas Euyang, Zanele Munyikwa et al. (+1 more)

A set of exposure scores calculated in 2023 has become a central empirical input to the future of work debate. Produced by Eloundou et al. (2023) and referred to here as the GPTs are GPTs scores, they define exposure as the share of occupational tasks a large language model can assist with. This work is a genuine methodological contribution, but as the scores travel from the time and place they were produced, the limitations the authors named do not always travel with them. Two gaps have widened as a result. The first is structural, between what static exposure scores measure and what policy questions actually require. Taking the diffusion of these scores as a case study, we show how their temporal, geographic, and ontological limitations compound in policy-facing analyses, and we survey five families of research responding to these limits: dynamic and benchmark-based measures, ensemble methods, task-framework extensions, worker-centered metrics, and adoption and usage data. The second gap is the one we argue needs more attention: the coordination between researchers and policymakers. The policy-relevant work which ask who is harmed, who benefits, how, and when, continues to reference the static GPTs are GPTs scores without engagement with the methodological updates that would let these questions be answered more reliably. We then ask what additional steps towards navigating uncertainty remain: ex-post frameworks and the deliberate, political work of reimagining what futures are worthy of building towards are. Closing the research-policy gap is a shared task: policymakers must widen their evidence base, engage workers as epistemic partners, and shift from prediction to preparedness; researchers must build data infrastructure, adopt participatory methods, and write with policymakers in mind. Better measurement matters, but it will not close the second gap alone.
Read the full abstract

All authors Campbell Lund, Thomas Euyang, Zanele Munyikwa, Marzieh Fadaee

Artificial Intelligence

AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring

Yansong Liu, Li-Hsi Lin, Pramit Khetrapal et al. (+3 more)

Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure. The Quality of Recovery (QoR-15) survey is the gold-standard instrument for this purpose. It was designed and validated for occasional in-hospital assessment, yet remote monitoring now administers it to patients daily. In our own post-surgical deployment, only 55% of patients submitted the survey more than 14 days of 30 monitoring days. We developed QoR-compact, a five-item daily input for the RPM prediction pathway. Setting a deployment-driven target of one-third of the daily items, we exhaustively evaluated all 3,003 five-question subsets of the QoR-15 and tested whether the best of them matches the full instrument in predicting near-term postoperative recovery severity. QoR-compact achieves a mean AUC-ROC of 0.968 (95% CI 0.915-0.988), statistically comparable to the 0.964 baseline obtained with one-third of the items. Patient-level backtesting indicates that it tracks readmission events as faithfully as the full form. Its five items span the physical and psychological axes of recovery: Q3 (feeling rested), Q9 (feeling comfortable and in control), Q10 (general well-being), Q12 (severe pain), and Q14 (feeling worried or anxious). The QoR-15 remains the gold-standard measure of recovery; QoR-compact complements it as a shorter daily input designed for prediction. This parity provides the basis for a prospective study of whether a lighter daily input is, in turn, completed more consistently. External validation on larger cohorts is required before clinical use.
Read the full abstract

All authors Yansong Liu, Li-Hsi Lin, Pramit Khetrapal, Ronnie Stafford, John Kelly, Ivana Drobnjak

Artificial Intelligence · Cross-listed from cs.LG

DiT-Reward: Generative Representations for Text-to-Image Reward Modeling

Yuanming Yang, Guoqing Ma, Bo Wang et al. (+5 more)

Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative representation learning. To this end, we introduce DiT-Reward, which converts a pretrained text-to-image Diffusion Transformer into a reward model by processing near-clean image latents and aggregating text-conditioned image representations across transformer layers. Under the same training data mixture as HPSv3, DiT-Reward outperforms HPSv3 on all four evaluated preference benchmarks, reaching 85.6% on HPDv2 and 77.6% on HPDv3. When the generative backbone is frozen, a lightweight learned head can still extract meaningful preference predictions from its representations. Probing across depth further reveals that downstream reward performance is strongest in the middle-to-late layers and benefits from combining representations across different stages. We also observe consistent positive scaling with generative backbone capacity. Finally, when used to optimize Stable Diffusion 3.5 Large with Flow-GRPO, DiT-Reward outperforms HPSv3 along the matched training trajectory, with particularly clear gains in realism. Direct latent scoring also achieves a 1.65x inference speedup over HPSv3 with comparable peak memory. These results show that pretrained generative DiTs provide transferable representations for reward modeling and policy optimization.
Read the full abstract

All authors Yuanming Yang, Guoqing Ma, Bo Wang, Yuan Zhang, Wei Tang, Chenyi Li, Haoyang Huang, Nan Duan

Artificial Intelligence · Cross-listed from cs.RO

RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models

Ulas Berk Karli and Tesca Fitzgerald

Vision-Language-Action (VLA) models are commonly fine-tuned through passive imitation learning, where additional demonstrations are collected for tasks where the policy performs poorly. This approach incurs several downsides: it requires the robot to fail before data collection is triggered, provides little guidance about which states require supervision, and wastes demonstrator effort on redundant parts of the task where the policy already performs well. In this paper, we propose an active, continual learning paradigm for VLAs. We demonstrate that active, uncertainty-guided data collection leads to more efficient fine-tuning than when using passively-collected demonstrations. However, we also find that fine-tuning only on actively-collected recovery data leads to catastrophic forgetting. We evaluate techniques for continual learning, including replay-based data mixing and elastic weight consolidation, and identify tradeoffs between plasticity to uncertainty-guided recovery data and retention of previously learned behaviors. Overall, our work contributes an empirical study of active continual learning for autoregressive VLAs, establishing that uncertainty-guided recovery demonstrations can improve adaptation efficiency while also revealing open challenges when targeted new data is incorporated into large robot policies.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

Data Selection Through Iterative Self-Filtering for Vision-Language Settings

Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M. Moss et al. (+1 more)

The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, resulting in sizeable datasets that can be very noisy. Attempts to mitigate this obstacle to producing performant vision-language models have so far involved heuristics, curated reference datasets, and using pre-trained models. Here we propose a novel, bootstrapped method in which a CLIP model is trained on an evolving, self-selected dataset. This evolving dataset constitutes a balance of filtered, highly probable clean samples as well as diverse samples from the entire distribution. Our proposed Self-Filtering method iterates between training the model and selecting a subsequently improved data mixture. Training on vision-language datasets filtered by the proposed approach improves downstream performance without the need for additional data or pre-trained models.
Read the full abstract

All authors Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M. Moss, Aaron Courville

Artificial Intelligence · Cross-listed from cs.LG

Discovering Latent Groups for Robust Classification

Ankur Garg, Ulrich Aïvodji, Samira Ebrahimi Kahou et al. (+1 more)

Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. Existing methods address this by adjusting network parameters, guided either by subgroup annotations or inferred pseudo-group labels. Yet at inference, these methods produce only a class prediction, with no insight into a sample's latent subgroup. We propose neural classification trees (NCT), a framework that achieves robustness by encoding subgroup structure in its tree-shaped architecture. By routing each sample to an "easy" or "hard" node of this tree - based on prediction correctness - and reusing these routes as pseudo-labels for the next iteration, NCT disentangles conflicting subgroups, without requiring subgroup supervision. We evaluate NCT on five benchmarks spanning binary and multi-class spurious correlations. Our experiments show that the learned tree topology provides strong interpretability by consistently isolating minority subgroups, which provides a transparent mapping between the model architecture and the data's latent group structure, while yielding competitive robustness with state-of-the-art methods.
Read the full abstract

All authors Ankur Garg, Ulrich Aïvodji, Samira Ebrahimi Kahou, Vincent Michalski

Artificial Intelligence

Causal Discovery in the Era of Agents

Yujia Zheng, Vishal Verma, Mantej Gill et al. (+3 more)

Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as priors and constraints. These approaches promise faster analysis, but they also obscure whether a causal evidence is supported by data and assumptions or by textual associations, prompt artifacts and hallucinated mechanisms. We argue for a different role for agents in causal discovery. Agents should inspect data, retrieve context, explain method assumptions and clarify graph outputs, but they should not supply edges, orientations, priors, constraints or causal conclusions. We propose the principle that agents assist the workflow, while causal claims remain grounded in data, explicit assumptions, formal algorithms, diagnostics and user or domain-expert decisions. We instantiate this principle in causal-learn+, an online platform that coordinates data analysis, preprocessing, method recommendation, expert-knowledge incorporation, formal discovery and interpretation around the algorithmic ecosystem of causal-learn. A case study on Big Five personality data illustrates agent-assisted pipeline of causal discovery without turning language-model unreliability into causal evidence. The platform is available at causallearn.com.
Read the full abstract

All authors Yujia Zheng, Vishal Verma, Mantej Gill, Haoyue Dai, Peter Spirtes, Kun Zhang

Artificial Intelligence · Cross-listed from cs.LG

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

Tianyi Li and Zhiqiang Shen

Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their scalability and effectiveness for large pretrained transformers. We propose a novel and scalable framework for enabling LMC-based model merging to billion-parameter pretrained transformers. Our method applies properly parameterized functionality-preserving weight transformations to align functionally equivalent solutions, and introduces a dual learning procedure in which both models jointly learn their corresponding transformations toward a shared linear interpolation path. This bidirectional optimization substantially reduces interpolation barriers and enables more reliable merging across large-scale architectures. Empirically, we show that our approach achieves near-zero loss barriers on WikiText for language models with medium-sized parameters, representing, to our knowledge, the first demonstration of near-barrier-free linear connectivity at this scale. In the vision domain, ViT-L maintains above 69% ImageNet top-1 accuracy throughout the interpolation path, while modern billion-parameter LLMs exhibit only small loss barriers. These results suggest that properly resolving parameter symmetries enables large pretrained Transformers to be connected and merged through simple linear paths with substantially improved interpolation performance. Code: https://github.com/VILA-Lab/Dual-Learned-Matching .
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

Mohamed Nagy, Naoufel Werghi, Jorge Dias et al. (+1 more)

The tracking-by-detection paradigm in multi-object tracking (MOT) typically relies on static appearance descriptors to complement motion estimation. However, these descriptors are frame-independent, limiting their robustness as visual cues. Since such descriptors are often obtained from computationally intensive pretrained backbones, real-time MOT systems frequently abandon appearance cues altogether and rely solely on motion prediction and geometric association. In this work, we introduce Polycepta, an object-centric appearance state estimation framework that reformulates appearance modeling as a recursive estimation problem rather than a frame-wise matching task. Polycepta constructs and continuously updates an independent appearance state for each tracked object, enabling future appearance representations to be estimated from accumulated observations. Polycepta is encouraged to learn the appearance-state construction of object-specific representations rather than memorize them through a proposed learning strategy, enabling appearance estimation for unseen classes. A key property of Polycepta is that the quality of appearance estimation improves as object states evolve during inference. While conventional appearance descriptors remain static or degrade over time, Polycepta progressively refines appearance estimates as additional observations are accumulated. Extensive experiments on KITTI, the Waymo Open Dataset, and MOT17 demonstrate consistent reductions in identity switches and improvements in tracking performance when integrated into the tracking-by-detection pipelines. Polycepta operates at 90.57 Hz and delivers state-of-the-art performance on the KITTI benchmark, achieving a MOTA of 92.27%.
Read the full abstract

All authors Mohamed Nagy, Naoufel Werghi, Jorge Dias, Majid Khonji

Artificial Intelligence

SPIRAL: Learning to Search and Aggregate

Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li et al. (+5 more)

Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives – sequential reasoning within a trace, independently sampled parallel traces, and aggregation of multiple reasoning traces into a final response. During post-training, however, language models are optimized only for sequential reasoning within a single trace. We introduce Sequential-Parallel-Aggregative Reinforcement Learning (SPIRAL), a framework in which a language model is trained to use all three primitives, as part of a unified inference compute pipeline. Concretely, the language model first samples a set of independent traces in parallel, each produced through sequential chain-of-thought reasoning, and then generates a final aggregation trace conditioned on those traces; all components are optimized end-to-end against the reward of the final aggregated response. To train this system, SPIRAL uses set reinforcement learning to teach models to produce a set of traces that are collectively useful for an aggregator and standard reinforcement learning to teach models to aggregate the set into improved final responses. Our experiments on reasoning tasks show that SPIRAL effectively scales with inference compute, outperforming GRPO by up to 11$\times$ scaling efficiency and 15% higher performance when all three compute primitives are scaled.
Read the full abstract

All authors Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li, Omar Shaikh, Yoonho Lee, Dorsa Sadigh, Chelsea Finn, Noah Goodman

Artificial Intelligence

TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models

Guangyu Jiang, Sizhe Tang, Mahdi Imani et al. (+2 more)

Ill-posed questions, including those involving ambiguity, under-specification, or conflicting statements, may admit no valid answer or multiple plausible answers, posing a significant challenge for large language models (LLMs) despite their otherwise strong performance. Existing work often treats LLM reasoning as a black box and focuses on input-output analysis. Can a compact, unified topological representation of internal model states capture diverse sources of ill-posedness and steer reasoning toward responses appropriate to each source? To this end, we study the internal state from a topological perspective by treating the contextual hidden states of its prompt tokens at a single transformer layer as a point cloud, capturing the input problem's relational structure as encoded by the model. Our analysis shows that zero- and one-dimensional persistent homology—tracking how connected components merge as the distance threshold increases ($H_0$) and the emergence and filling of one-dimensional loops in the filtration ($H_1$), respectively—yield seven compact descriptors of ill-posedness that also serve as control signals for steering model reasoning. Thus, we develop a topology-conditioned steering mechanism. It retrieves topologically similar positive and negative examples for each query to form a local activation-space contrast. The resulting query-specific direction modifies internal states during prefill and decoding, guiding the model's responses toward suitable abstention or clarification tailored to the underlying source of ill-posedness. Empirical evaluations on two datasets and open-weight models spanning four families demonstrate the effectiveness of this compact representation for ill-posedness classification, while topology-conditioning significantly improved steering performance.
Read the full abstract

All authors Guangyu Jiang, Sizhe Tang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan