AI 연구 논문 데일리

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

ACECODER: Acing Coder RL via Automated Test-Case Synthesis

Inverse Bridge Matching Distillation

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification

Federated Sketching LoRA: On-Device Collaborative Fine-Tuning of Large Language Models

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense