HuggingFace
Attending to Multimodal Generation One Token at a Time
Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic infor...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules
We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks su...
HuggingFace
SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control
Geometry-conditioned 3D scene generation enables the creation of 3D environments from user-provided geometry, offerin...
HuggingFace
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases ...
HuggingFace
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little ...
HuggingFace
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-sp...
HuggingFace
Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, th...
HuggingFace
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchan...
arXiv
AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models
Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical ...
arXiv
Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms
The dairy industry in Ireland has a large potential for the integration of renewable energy and the reduction of carb...
arXiv
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine
Live sports commentary is grounded generation under a deadline: statements concern real, named athletes, the groundin...
arXiv
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail,...