3 citations · 5 across the 10 of their papers we have counts for
6 papers · 1 filter
Latent On-Policy Self-Distillation
Guibin Zhang, Jiayang Lyu, Ran Sun +4
Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effecti…
SuperThoughts: Reasoning Tokens in Superposition
Zheyang Xiong, Shivam Garg, Max Yu +4
Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation. While recent works explore reasoning in cont…
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Yong Lin, Shange Tang, Bohan Lyu +17
We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and rein…
Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
Yikai Wu, Haoyu Zhao, Sanjeev Arora
AI methods, such as generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, especially NP-hard ones. This paper compar…
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Kaifeng Lyu, Haoyu Zhao, Xinran Gu +3
Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datase…
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli +3
We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capt…