Related papers: Exploiting Tree Structure for Credit Assignment in…

Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free algorithms such as Group Relative Policy Optimization (GRPO)…

Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emerging as a leading approach. However, GRPO and its variants are…

Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for…

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a…

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Recent advancements in the reasoning capabilities of large language models (LLMs) show that employing group relative policy optimization (GRPO) algorithm for reinforcement learning (RL) training allows the models to use more…

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However, training LLMs for this task requires sufficient data, a robust environment, and the process is often…

Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at $\geq$7B parameters, with limited systematic study of…

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable…

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen…

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce…

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…