arXiv:2604.16871v1 Announce Type: new Abstract: Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concepts, such as “left of” or “close by”, serve as foundational building blocks that structure how agents perceive and act. However, conventional approaches require human experts to manually define these concepts, limiting adaptability […]
Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction
arXiv:2604.17328v1 Announce Type: cross Abstract: This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should […]
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection
arXiv:2604.04815v2 Announce Type: replace-cross Abstract: The rapid development of Large Language Models (LLMs) has transformed fake news detection and fact-checking tasks from simple classification to complex reasoning. However, evaluation frameworks have not kept pace. Current benchmarks are static, making them vulnerable to benchmark data contamination (BDC) and ineffective at assessing reasoning under temporal uncertainty. To […]
EgoEsportsQA: An Egocentric Video Benchmark for Perception and Reasoning in Esports
arXiv:2604.12320v2 Announce Type: replace-cross Abstract: While video large language models (Video-LLMs) excel in understanding slow-paced, real-world egocentric videos, their capabilities in high-velocity, information-dense virtual environments remain under-explored. Existing benchmarks focus on daily activities, yet lack a rigorous testbed for evaluating fast, rule-bound reasoning in virtual scenarios. To fill this gap, we introduce EgoEsportsQA, a pioneering […]
A Sugeno Integral View of Binarized Neural Network Inference
arXiv:2604.17967v1 Announce Type: new Abstract: In this article, we establish a precise connection between binarized neural networks (BNNs) and Sugeno integrals. The advantage of the Sugeno integral is that it provides a framework for representing the importance of inputs and their interactions, while being equivalent to a set of if-then rules. For a hidden BNN […]
What Is Actually Being Annotated? Inter-Prompt Reliability as a Measurement Problem in LLM-Based Social Science Labeling
arXiv:2604.16413v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for annotation in computational social science, yet their methodological reliability under prompt variation remains unclear. This paper introduces Inter-Prompt Reliability (IPR), a framework for evaluating the stability of LLM outputs across semantically equivalent but linguistically varied prompts. Drawing on Inter-Rater Reliability, IPR is […]
SAND: The Challenge on Speech Analysis for Neurodegenerative Disease Assessment
arXiv:2604.16445v1 Announce Type: cross Abstract: Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the development of algorithms to support the early diagnosis of neurodegenerative diseases, including Amyotrophic Lateral Sclerosis (ALS). Voice changes in subjects suffering from ALS typically manifest as progressive dysarthria, which is […]
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
arXiv:2604.16335v1 Announce Type: cross Abstract: Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as whether all unit tests pass. While these binary signals reflect whether the final solution is correct, they provide little guidance for shaping intermediate behaviors during multi-step […]
Brain-CLIPLM: Decoding Compressed Semantic Representations in EEG for Language Reconstruction
arXiv:2604.16370v1 Announce Type: cross Abstract: Decoding natural language from non-invasive electroencephalography (EEG) remains fundamentally limited by low signal-to-noise ratio and restricted information bandwidth. This raises a fundamental question regarding whether sentence-level linguistic structure can be reliably recovered from such signals. In this work, we suggest that this assumption may not hold under realistic information constraints, […]
One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction
arXiv:2604.18344v1 Announce Type: new Abstract: Knowledge Graphs (KGs) are composed of triples, and the goal of Knowledge Graph Completion (KGC) is to infer the missing factual triples. Traditional KGC tasks predict missing elements in a triple given one or two of its elements. As a more realistic task, the Triple Set Prediction (TSP) task aims […]
A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
arXiv:2604.10210v1 Announce Type: cross Abstract: Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), […]
Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures
arXiv:2604.16042v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation methods that interpret trained models through external approximations. In contrast, intrinsic interpretability, which builds transparency directly into model […]