arXiv:2504.04143v4 Announce Type: replace-cross Abstract: Human aging is marked by a steady rise in the risk of dying with age-a process demographers call senescence. Over the past century, life expectancy has risen dramatically, but is this because we are aging slower, or simply starting it later? Vaupel hypothesizes that the pace at which individuals age […]
HPS: Hard Preference Sampling for Human Preference Alignment
arXiv:2502.14400v5 Announce Type: replace Abstract: Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett-Luce (PL) and Bradley-Terry (BT) models have shown promise, they face challenges such as poor handling of harmful content, inefficient use of dispreferred responses, and, specifically […]
Agentic Harness for Real-World Compilers
arXiv:2603.20075v1 Announce Type: cross Abstract: Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs pose unique challenges due to their complexity, deep cross-domain expertise requirements, and sparse, non-descriptive bug reports, necessitating compiler-specific tools. To bridge the gap, we introduce […]
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
arXiv:2509.24897v2 Announce Type: replace Abstract: The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, […]
AI Agents Can Already Autonomously Perform Experimental High Energy Physics
arXiv:2603.20179v1 Announce Type: cross Abstract: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipeline with minimal expert-curated input. Given access to a HEP dataset, an execution framework, and a corpus of prior experimental literature, we find that Claude Code succeeds in automating all […]
DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models
arXiv:2603.18048v2 Announce Type: replace Abstract: Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematically study this question, we introduce DEAF (Diagnostic Evaluation of Acoustic Faithfulness), a benchmark of over 2,700 conflict […]
Teaching an Agent to Sketch One Part at a Time
arXiv:2603.19500v1 Announce Type: new Abstract: We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, […]
Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study
arXiv:2502.19095v2 Announce Type: replace-cross Abstract: Cross-site scripting (XSS) poses a significant threat to web application security. While Deep Learning (DL) has shown remarkable success in detecting XSS attacks, it remains vulnerable to adversarial attacks due to the discontinuous nature of the mapping between the input (i.e., the attack) and the output (i.e., the prediction of […]
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
arXiv:2603.19918v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery often yield brittle boundaries on fine-grained, look-alike categories. We introduce the Analogical Textual Concept Generator (ATCG), a plug-and-play module […]
Adaptive Relative Pose Estimation Framework with Dual Noise Tuning for Safe Approaching Maneuvers
arXiv:2507.16214v3 Announce Type: replace-cross Abstract: Accurate and robust relative pose estimation is crucial for enabling challenging Active Debris Removal (ADR) missions targeting tumbling derelict satellites such as ESA’s ENVISAT. This work presents a complete pipeline integrating advanced computer vision techniques with adaptive nonlinear filtering to address this challenge. A Convolutional Neural Network (CNN), enhanced with […]
Hyperagents
arXiv:2603.19461v1 Announce Type: new Abstract: Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin G”odel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly […]
CARES: Context-Aware Resolution Selector for VLMs
arXiv:2510.19496v2 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total tokens, resulting in high compute and latency, even when low-resolution images would suffice. We introduce emphCARES-a textbfContext-textbfAware textbfResolution textbfSelector, a lightweight preprocessing module that, […]