…Ziyan Liu , , Yuzhe Gu , , , , , , Wenwei Zhang , Abstract ThoughtFold addresses over-thinking in large reasoning models by using fine-grained preference learning to identify and eliminate redundant explorations in chain-of-thought reasoning…
…Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. We identify the lack…
…Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The…
…Uzunoğlu on Jun 9 Center for Language and Speech Processing @ JHU Authors: Arda Uzunoglu , , Abstract Trust functions enable effective weak-to-strong generalization by identifying reliable weak labels for training, achieving performance…
…Jinheon Baek , , Sangwoo Park , Woongyeong Yeo , , , , Abstract OmniRetrieval is a framework that handles diverse knowledge sources by identifying appropriate repositories and dispatching native queries to their respective execution engines, outperforming single-source…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct We introduce EMMA, a physics-informed multimodal framework that recovers all identifiable dynamical parameters of a system directly from raw video, audio, and image…
…We call this failure mode memory confabulation and introduce the Reflection Repetition Rate (RRR), a log-based metric that detects repeated reliance on incorrect reflective content. Using RRR, we identify 16 frozen…
…These tasks jointly assess model performance across visual generation , trajectory following , and memory . Evaluating 14 representative world models , we identify key limitations and provide insights for future research. The iWorld-Bench model…
…We conducted pre-release testing across domains identified in our Frontier AI Framework as potentially presenting catastrophic risks , and also evaluated the model's misaligned propensities . Our assessment found that CWM does…
…Sinclair Schneider , , Abstract A computational framework combining prompt-based filtering and unsupervised clustering identifies manipulative political narrative clusters from social media posts without requiring predefined categories. AI-generated summary We present a…