3 papers
cs.LG2026
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Ruiying Peng, Mengyu Yang, Jing Lei +3
Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is no…
cs.CV2026
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
Ruiying Peng, Xueyu Wu, Jing Lei +3
Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify…
cs.CL2025
Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs
Yichun Yin, Wenyong Huang, Kaikai Song +49
We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field…