4 papers
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Liu Qing, Ou Wu, Yi Du
Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local heuristics and rarely formulate token selection as a principled valuation…
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
Minglai Yang, Xinyan Velocity Yu, Pengyuan Li +22
Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OC…
From Noise to Control: Parameterized Diffusion Policies
Renhao Zhang, Haotian Fu, Mingxi Jia +3
We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior ma…
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Vighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum +3
Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the traini…