相关论文: LiteGUI: Distilling Compact GUI Agents with Reinfo…

Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However, their performance is often constrained by the scarcity of…

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…

The training of high-quality, robust machine learning models for speech-driven 3D facial animation requires a large, diverse dataset of high-quality audio-animation pairs. To overcome the lack of such a dataset, recent work has introduced…

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,…

Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency,…

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or…

Hierarchical policies for language-conditioned manipulation decompose tasks into subgoals, where a high-level planner guides a low-level controller. However, these hierarchical agents often fail because the planner generates subgoals…

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as little as one step of…

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is…

Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the…

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…

Recent advancements in dataset distillation have demonstrated the significant benefits of employing soft labels generated by pre-trained teacher models. In this paper, we introduce a novel perspective by emphasizing the full utilization of…

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…