Related papers: From Passive Observer to Active Critic: Reinforcem…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution…

Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on…

Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However, many existing MBRL methods rely on combining greedy…

Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the…

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…

Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL training remain poorly understood. This work identifies two…

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered…

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that the learned policy…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically…

The shift from the understanding and prediction of processes to their optimization offers great benefits to businesses and other organizations. Precisely timed process interventions are the cornerstones of effective optimization.…