8 papers
Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning
Deqian Kong, Minglu Zhao, Aoyang Qin +10
Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We int…
Generative Actor Critic
Aoyang Qin, Deqian Kong, Wei Wang +3
Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with on…
Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
Bo Pang, Deqian Kong, Silvio Savarese +2
Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two…
FFT-Accelerated Auxiliary Variable MCMC for Fermionic Lattice Models: A Determinant-Free Approach with Complexity
Deqian Kong, Shi Feng, Jianwen Xie +1
We introduce a Markov Chain Monte Carlo (MCMC) algorithm that dramatically accelerates the simulation of quantum many-body systems, a grand challenge in computational science. Stat…
Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
Minglu Zhao, Dehong Xu, Deqian Kong +2
The hippocampus supports spatial navigation by encoding cognitive maps through collective place cell activity. We model the place cell population as non-negative spatial embeddings…
Latent Adaptive Planner for Dynamic Manipulation
Donghun Noh, Deqian Kong, Minglu Zhao +4
We present the Latent Adaptive Planner (LAP), a trajectory-level latent-variable policy for dynamic nonprehensile manipulation (e.g., box catching) that formulates planning as infe…