49 citations · 49 across the 7 of their papers we have counts for
9 papers
Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery
Peter Chen, Wotao Yin
AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, executi…
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
Peter Chen, Xi Chen
We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep minimax search and M…
Reward-free Alignment for Conflicting Objectives
Peter Chen, Xiaopeng Li, Xi Chen +1
Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflictin…
Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
Peter Chen, Xiaopeng Li, Ziniu Li +3
This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Model…
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
Jiacheng Guo, Ling Yang, Peter Chen +6
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenE…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Peter Chen, Xiaopeng Li, Ziniu Li +2
Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimiz…
ComPO: Preference Alignment via Comparison Oracles
Peter Chen, Xi Chen, Wotao Yin +1
Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and like…
Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities
Vicky Zayats, Peter Chen, Melissa Ferrari +1
Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges.…