Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.28236v1 Announce Type: new Abstract: Long-horizon embodied interaction requires agents to retain and continually update information about the environment as they observe, act, and encounte...
arXiv:2609.27094v1 Announce Type: cross Abstract: Automatic tagging is a core task in Music Information Retrieval (MIR), yet most tagging systems exploit only audio. Live music performance is inheren...
arXiv:2605.16080v2 Announce Type: replace Abstract: The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image fo...
arXiv:2609.23407v2 Announce Type: replace-cross Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challengin...
arXiv:2508.13680v5 Announce Type: replace-cross Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (V...
arXiv:2609.26855v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-a...
SoLiD26 is a curated dataset of 15.4 million first‑principles atomic structures for solid‑liquid interfaces, comprising up to 576 atoms and 15 chemical elements. The data were generated from density functional theory calculations, mainly ab initio molecular dynamics, and include aqueous coinage metal interfaces, electrode‑electrolyte systems, and bulk references. Each record contains atomic species, positions, cell parameters, periodic boundary conditions, potential energy, and atomic forces, all computed with VASP using the PBE functional and D3 dispersion corrections.
The paper audits silent failures in agent-to-tool interactions within the ToolUniverse environment, focusing on 15 scientific tools. It identifies 91 failures—primarily missing data or inconsistent search/filtering—occurring mainly in the API and wrapper layers, and shows how these silent failures can propagate downstream into seemingly valid outputs. The authors propose contextual reliability and recommend testing, disclosure, monitoring, and measurement strategies for the agent-tool pipeline.
arXiv:2609.27355v1 Announce Type: cross Abstract: Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post...
Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large language models (LLMs). While their group-normal...
Recent advances in video object segmentation with Multimodal Large Language Model (MLLM) reasoning have demonstrated the effectiveness of using a single textual token, such as SEG, to predict segmenta...
Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs),...
Although hyperspectral images (HSIs) provide rich spectral-spatial information, accurate pixel-level classification remains challenging because of spectral-spatial heterogeneity and complex spatial st...
Removing an object from a real image requires more than synthesizing plausible content within a mask: the method must suppress residual object features, preserve the unedited scene, and generate repla...
Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is accessible at all. We present the Systemic Risk...
Long physiological recordings contain many routine measurements, while predictive information is often concentrated in rare events, sustained burden, and recurring temporal patterns. Masked autoencodi...
Electrocardiography (ECG) contains subject-specific morphology that supports biometric recognition, yet image-based performance depends on how the waveform is rendered. We introduce representative-mor...
Backtest auditing is a calibration problem: high flaw recall is not useful when the model falsely flags matched clean strategies. We build a 96-item paired benchmark in which every flawed backtest has...
Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth...
Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM...