4 papers
On-Policy Replay for Continual Supervised Fine-Tuning
Yan Chen, Taojie Zhu, Meng Zhang +4
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…
The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
Doguhan Yeke, Elif Su Temirel, Ananth Shreekumar +3
Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations into action plans. While prior…
TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?
Jieting Xiao, Yun Lin, Huizhen Qiu +10
While Large Language Models have achieved remarkable integration in various vertical scenarios, their deployment in the telecommunications domain remains exploratory due to the lac…
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
Taojie Zhu, Dongyang Xu, Ding Zou +4
Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability…