AI 연구 논문 데일리

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

Time Blindness: Why Video-Language Models Can't See What Humans Can?

Large Language Models for Data Synthesis

HardTests: Synthesizing High-Quality Test Cases for LLM Coding

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models

EXP-Bench: Can AI Conduct AI Research Experiments?

Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning

Vision Language Models are Biased

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

CLaSp: In-Context Layer Skip for Self-Speculative Decoding

EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering

Large Language Models are Locally Linear Mappings

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL

Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning

DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation

ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents

Role-Playing Evaluation for Large Language Models

Evaluating and Steering Modality Preferences in Multimodal Large Language Model

SiLVR: A Simple Language-based Video Reasoning Framework

Harnessing Large Language Models for Scientific Novelty Detection

un^2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows

Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts

Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks

TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis

GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training

Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities

LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation

Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings

The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It