The Alignment Waltz: Jointly Training Agents to Collaborate for Safety Paper • 2510.08240 • Published Oct 9 • 40
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning Paper • 2509.22621 • Published Sep 26 • 8
The Flaw of Averages: Quantifying Uniformity of Performance on Benchmarks Paper • 2509.25671 • Published Sep 30 • 6
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT Paper • 2509.19284 • Published Sep 23 • 22
The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure Paper • 2506.22724 • Published Jun 28 • 10
Certified Mitigation of Worst-Case LLM Copyright Infringement Paper • 2504.16046 • Published Apr 22 • 13
Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning Paper • 2503.04973 • Published Mar 6 • 26
Rank1: Test-Time Compute for Reranking in Information Retrieval Paper • 2502.18418 • Published Feb 25 • 28
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering Paper • 2502.13962 • Published Feb 19 • 28 • 4
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering Paper • 2502.13962 • Published Feb 19 • 28
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering Paper • 2502.13962 • Published Feb 19 • 28
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering Paper • 2502.13962 • Published Feb 19 • 28 • 4
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations Paper • 2412.13171 • Published Dec 17, 2024 • 35