본문으로 건너뛰기

#Alignment

40개의 포스트

[논문리뷰] From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

댓글 수 로딩 중

[논문리뷰] Proving and Improving the Platonic Representation Hypothesis with JEPAs

댓글 수 로딩 중

[논문리뷰] Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

댓글 수 로딩 중

[논문리뷰] Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

댓글 수 로딩 중

[논문리뷰] CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning

댓글 수 로딩 중

[논문리뷰] Enhancing Rubric-based RL via Self-Distillation

댓글 수 로딩 중

[논문리뷰] Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

댓글 수 로딩 중

[논문리뷰] The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

댓글 수 로딩 중

[논문리뷰] Trajectory-Refined Distillation

댓글 수 로딩 중

[논문리뷰] RobotValues: Evaluating Household Robots When Human Values Conflict

댓글 수 로딩 중

[논문리뷰] Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

댓글 수 로딩 중

[논문리뷰] FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

댓글 수 로딩 중

[논문리뷰] The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

댓글 수 로딩 중

[논문리뷰] Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

댓글 수 로딩 중

[논문리뷰] AI & Human Co-Improvement for Safer Co-Superintelligence

댓글 수 로딩 중

[논문리뷰] Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

댓글 수 로딩 중