We have 5 of 17 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
DecoEvo (Decoupled Co-Evolution), which co-evolves a solver skill and a rubric-generator skill under decoupled objectives without using gold rubrics during optimization, is introduced.
Multi-Agent Protocol Distillation (MAPD), a joint distillation and RL framework uses a structured, style-normalized protocol as an intermediate representation that generalizes robustly across diverse proprietary teachers while effectively mitigating the student policy from style drift and verbosity degeneration.
PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it, is introduced.
DynaRule is proposed, an end-to-end framework that injects the given rules into the KV cache and turns retrieval into an internal, learnable, step-wise process, and can re-attend to the most relevant rules at each step, dynamically replacing outdated ones to support more stable multi-step reasoning.
This work systematically study weight-only post-training quantization across bit-widths, quantization methods, model scales and downstream tasks and establishes that quantization degradation is governed by how errors are introduced at the source and how they accumulate across the network.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
