arXiv:2605.15995v1 Announce Type: cross Abstract: Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems. In such settings, representations are better understood as latent states capturing underlying system dynamics, rather than as mere compressed summaries of observations. Yet current approaches remain fragmented, relying on distinct — […]
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
arXiv:2602.20207v3 Announce Type: replace-cross Abstract: Knowledge editing in Large Language Models (LLMs) aims to update the model’s prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize […]
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
arXiv:2605.15764v1 Announce Type: cross Abstract: Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to identify who interacts with whom in multi-person videos. We introduce GRASP, a large-scale social reasoning dataset that connects high-level social QA with fine-grained gaze and deictic gesture events. GRASP contains 290K […]
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
arXiv:2605.10989v2 Announce Type: replace-cross Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted designs that suffer from gradient mismatch problem and information loss induced by fixed-range gradient clipping. […]
X-SYNTH: Beyond Retrieval — Enterprise Context Synthesis from Observed Human Attention
arXiv:2605.15505v1 Announce Type: new Abstract: In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication channels. What is stored is system state, a lossy representation of the work that actually happened [2, 52]. The prevailing approach [17, 31, 34, 36] retrieves by matching […]
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
arXiv:2605.15984v1 Announce Type: cross Abstract: Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic speech detection often neglect the contribution of paralinguistic cues, such as emotion, intonation, and speech rate, which are key to detecting speech toxicity. Moreover, current toxic speech datasets are predominantly text-based, […]
Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
arXiv:2605.15812v1 Announce Type: cross Abstract: Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents’ social behaviors […]
The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies
arXiv:2605.10799v2 Announce Type: replace-cross Abstract: Corruption studies, the standard tool for evaluating chain-of-thought (CoT) faithfulness, infer which steps are “computationally important” from accuracy loss when steps are corrupted. We show that when benchmark chains end with an explicit terminal answer line, as in GSM8K and MATH, these tests largely measure emphanswer placement rather than where […]
DPrivBench: Benchmarking LLMs’ Reasoning for Differential Privacy
arXiv:2604.15851v2 Announce Type: replace-cross Abstract: Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely on specialized verification languages that demand substantial domain expertise or remain semi-automated and require human-in-the-loop guidance. In […]
Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports
arXiv:2605.15978v1 Announce Type: cross Abstract: Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value […]
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
arXiv:2605.10052v2 Announce Type: replace-cross Abstract: As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent textbfCoordination Engineering, the ability to codify and systematically improve how multiple agents collaborate has emerged as a critical bottleneck. While single-agent skills can now be distributed as portable assets, multi-agent coordination protocols remain locked within framework-internal […]
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
arXiv:2605.15513v1 Announce Type: new Abstract: Parallel reasoning, where a generator samples many candidate solutions and an aggregator selects the best, is one of the most effective forms of test-time scaling in large language models, and pairwise self-verification has become its strongest aggregation primitive. Yet pairwise verification carries a heavy cost: each judgment reads two complete […]