Tag
The paper introduces GUI-SD-v2, a two-stage on-policy self-distillation framework for multi-turn GUI agents that enhances privilege following and guidance, achieving superior performance on AndroidWorld and MobileWorld benchmarks.
The paper proposes Abstract Token Curriculum (ATC), a curriculum learning framework that elicits effective continuous intermediate representations in LLMs without direct supervision, supported by theoretical and experimental evidence.
EnvCraft is an automated framework for synthesizing executable environments to address the scarcity in Agentic RL training, showing significant performance gains on claw-like and general tool-use benchmarks using Qwen models.
RAPTOR is a role-aware framework for differentially private fine-tuning of Mixture-of-Experts models, addressing failure modes like clipping interference and noise dilution, with experimental improvements over standard DP baselines.
This paper introduces TKFQA, a counterfactual benchmark of 10,130 QA pairs over tables, texts, and knowledge graphs for evaluating LLM factuality consistency and order-robust reasoning, and proposes ORLF, a training framework that improves reasoning-chain accuracy and reduces input-order sensitivity.
iFAN is a training framework that improves mask transformers for segmentation by aligning query ranking with mask quality and distilling intermediate predictions to the final layer, yielding consistent gains across benchmarks.
MiniWorld is a reproducible framework for training video world models from scratch using a block-causal Video Diffusion Transformer with Flow Matching, enabling efficient streaming generation and trainable in days on a single 8-GPU server.
Molt is a PyTorch-native training framework for agentic reinforcement learning designed to be compact and clean for easy modification, while achieving performance comparable to Megatron-based stacks.
Introduces a framework for training a harness to improve task LLM capabilities in a model-agnostic and task-environment-agnostic way, with results on Terminal Bench and SWE-Bench.
PRIME-RL is a framework for large-scale asynchronous reinforcement learning, designed to be hackable and scale to 1000+ GPUs with support for various models and environments.
Introduces Pyligent, a training framework that uses task validators to label failures and teaches LLMs to backtrack during reasoning, improving solve rates on hidden graphs, Sudoku, and Blocksworld.
DeepSeek open-sourced DeepSpec, a full-stack codebase for training and evaluating draft models for speculative decoding, enabling 60-85% faster generation. It includes data preparation, training, and evaluation scripts with support for multiple draft model algorithms (DSpark, DFlash, Eagle3).
This paper introduces RPCL, a training-only framework for robust pair confidence learning in multimodal emotion-cause pair extraction, which improves discriminative separation of gold pairs from hard negatives and achieves significant gains in Pair F1 and AUPRC on three datasets.
A call for open training frameworks in AI research, introducing FeynRL, a modular and explicit framework for RL post-training of LLMs, VLMs, and agents, designed to make training processes visible and modifiable.
This paper introduces RePro, a framework that trains LLM agents to self-generate progress signals through a forward-then-reflect rollout paradigm, achieving up to 12% absolute success rate gains on WebShop, ALFWorld, and Sokoban benchmarks.
Orchard is an open-source framework for scalable agentic modeling that enables training diverse autonomous agents, achieving state-of-the-art results on coding, GUI navigation, and personal assistance tasks.
EasyVideoR1 is an efficient reinforcement learning framework for training large vision-language models on video understanding tasks, featuring offline preprocessing with tensor caching for 1.47x throughput improvement, a task-aware reward system covering 11 problem types, and evaluation across 22 video benchmarks. It also supports joint image-video training and a mixed offline-online data training paradigm.
Agent Lightning introduces a flexible reinforcement learning framework for training large language models in AI agents, achieving decoupling between agent execution and training to handle complex interactions.
OpenAI releases RL-Teacher, an open-source tool for training AI systems through human feedback instead of hand-crafted reward functions, with applications to safe AI development and complex reinforcement learning problems.
This article provides a detailed introduction to the basic concepts and terminology of model fine-tuning, including key knowledge points such as pre-training, supervised fine-tuning, and LoRA, suitable for beginners to understand.