AI研究論文每日精選

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals

Unlocking Continual Learning Abilities in Language Models

Aligning Diffusion Models with Noise-Conditioned Perception

APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets

DiffusionPDE: Generative PDE-Solving Under Partial Observation

LongIns: A Challenging Long-context Instruction-based Exam for LLMs

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning

MotionBooth: Motion-Aware Customized Text-to-Video Generation

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation

On the Transformations across Reward Model, Parameter Update, and In-Context Prompt

FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models

DialSim: A Real-Time Simulator for Evaluating Long-Term Dialogue Understanding of Conversational Agents

Image Conductor: Precision Control for Interactive Video Synthesis

Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Large Language Models Assume People are More Rational than We Really are

Cross-Modality Safety Alignment