AI Research Papers Daily

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

Iterative Self-Training for Code Generation via Reinforced Re-Ranking

Mavors: Multi-granularity Video Representation for Multimodal Large Language Model

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models

DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

MIEB: Massive Image Embedding Benchmark

TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Reasoning Models Can Be Effective Without Thinking

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety

How new data permeates LLM knowledge and how to dilute it

3D CoCa: Contrastive Learners are 3D Captioners

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

DeepSeek vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?

MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion