Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features Paper • 2609.33463 • Published 10 days ago • 11
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning Paper • 2608.14277 • Published Aug 14 • 36
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent Paper • 2606.30616 • Published Jun 29 • 105
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads Paper • 2602.09443 • Published Feb 10 • 59
A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation Paper • 2601.22708 • Published Jan 30 • 1
P1: Mastering Physics Olympiads with Reinforcement Learning Paper • 2511.13612 • Published Nov 17, 2025 • 135
Biology Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models Paper • 2412.19191 • Published Dec 26, 2024
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning Paper • 2608.14277 • Published Aug 14 • 36
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning Paper • 2607.07708 • Published Jul 8 • 88
A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation Paper • 2601.22708 • Published Jan 30 • 1