Related papers: Self-Supervised On-Policy Distillation for Reasoni…

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the…

Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However,…

Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large language models. However, it faces a fundamental compute and memory asymmetry: rollout generation is…

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing…

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Vision-Language-Action Models (VLAs) have demonstrated remarkable generalization capabilities in real-world experiments. However, their success rates are often not on par with expert policies, and they require fine-tuning when the setup…

On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its standard advantage weighted…

On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate…

Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the…

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular programs that mix together multiple LM calls with distinct…

Decision transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static datasets and inherent architectural limitations.…

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its…

RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR…

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

On-policy reinforcement learning (RL) algorithms are typically characterized as algorithms that perform policy updates using i.i.d. trajectories collected by the agent's current policy. However, after observing only a finite number of…

Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression.…