일간 논문

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models

Parallel Scaling Law for Language Models

System Prompt Optimization with Meta-Learning

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

EnerVerse-AC: Envisioning Embodied Environments with Action Condition

End-to-End Vision Tokenizer Tuning

WorldPM: Scaling Human Preference Modeling

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation

Style Customization of Text-to-Vector Generation with Image Diffusion Priors

Depth Anything with Any Prior

PointArena: Probing Multimodal Grounding Through Language-Guided Pointing

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning

3D-Fixup: Advancing Photo Editing with 3D Priors

AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenge

ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking

QuXAI: Explainers for Hybrid Quantum Machine Learning Models

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection

Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware

MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real