Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.14754v1 Announce Type: new Abstract: Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV...
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suf...
arXiv:2610.15575v1 Announce Type: new Abstract: Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learne...
arXiv:2610.17738v1 Announce Type: new Abstract: End-to-end (E2E) full-duplex spoken language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriat...
arXiv:2610.15081v1 Announce Type: new Abstract: Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying gen...
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, bu...
arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a larg...
arXiv:2610.16661v1 Announce Type: new Abstract: An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this,...
arXiv:2610.17728v1 Announce Type: new Abstract: Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, inclu...
arXiv:2610.17740v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that...
arXiv:2610.16980v1 Announce Type: new Abstract: Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry profess...
arXiv:2610.18851v1 Announce Type: new Abstract: Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple...
arXiv:2610.18067v1 Announce Type: new Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further...
arXiv:2610.18092v1 Announce Type: new Abstract: Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However,...
arXiv:2610.18233v1 Announce Type: new Abstract: System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fa...
arXiv:2610.18449v1 Announce Type: new Abstract: AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide f...
arXiv:2610.14226v1 Announce Type: cross Abstract: Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation...
arXiv:2610.14000v1 Announce Type: cross Abstract: Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When ever...
arXiv:2610.15795v1 Announce Type: cross Abstract: Automated moderation systems are deployed at scale, yet they remain opaque to the users and moderators affected by their decisions, and their coverag...
arXiv:2610.16127v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored in the Architecture, Engineering, and Construction (AEC) domain, yet their reliability in regu...