Related papers: Power Distribution Bridges Sampling, Self-Reward R…

Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods…

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on…

Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective…

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…

The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes…

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are…

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches…

Large language models provide rich semantic priors and strong reasoning capabilities, making them promising auxiliary signals for recommendation. However, prevailing approaches either deploy LLMs as standalone recommender or apply global…

Current Reinforcement Learning (RL) methodologies for Large Language Models (LLMs) often rely on simplistic, outcome-based reward signals (e.g., final answer correctness), which limits the depth of learning from each interaction. This paper…

Intrinsic motivation, inspired by the psychology of developmental learning in infants, stimulates exploration in agents without relying solely on sparse external rewards. Existing methods in reinforcement learning like Random Network…

In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative. We identify a reward-density principle that governs this…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high training efficiency. Although these EDistilled LLMs achieve state-of-the-art (SOTA)…