Tracked topic
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Large language models solve complex problems by generating lengthy chains of explicit reasoning tokens. While effective, this makes reasoning expensive, length-sensitive, and constrained…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability…
…To demonstrate training utility, we collect rejection-sampled Qwen3.5 trajectories on the synthesized tasks and use them for supervised fine-tuning . Fine-tuning on these trajectories improves Qwen3.5-27B and…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and…