A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Guillermo Gallego, Tobi Delbrück, Garrick Orchard, et al.
A comprehensive survey of event-based vision, covering event camera principles, available sensors, processing algorithms, applications, and future challenges.
Yuji Cao, Huan Qi Zhao, Yuheng Cheng, et al.
This survey proposes a taxonomy of four roles for LLMs in reinforcement learning—information processor, reward designer, decision-maker, and generator—and reviews methods, challenges, and future directions.
Claude E. Shannon
Shannon extends his mathematical theory of communication to continuous signals and messages via a limiting process from the discrete case, revealing new effects and specializations.
Konstantinos I. Roumeliotis, Nikolaos D. Tselikas
This paper provides a preliminary review of ChatGPT, covering its training process, fundamental functionality, and a comprehensive literature review of early research.
Unknown
Longcodezip compresses long code contexts to enable efficient processing by code language models.
Unknown
The paper identifies a hidden bias in Process Reward Models caused by severe imbalance in step-level feedback and proposes PRISM to reward the right reasoning.
Unknown
The paper analyzes uncertainty calibration of process reward models, extending evaluation to a 72B parameter variant on MATH500 and AIME24-25 datasets.
Unknown
This paper shows that Process Reward Models can generalize from mathematical reasoning to code, enhancing LLM reasoning in test-time scaling across domains.
Unknown
This paper investigates process reward models for evaluating reasoning steps in thinking-with-images tasks, addressing the gap in text-centric PRM benchmarks.
Ning Liu
Proposes using cross-model consensus among LLMs as a jury to select correct reasoning chains, outperforming process reward models for test-time scaling.
Unknown
The paper investigates whether quality-diversity archive coverage can certify the robustness of process reward models under stress tests, finding that coverage alone is insufficient.
Unknown
OC-PRM introduces overcredit-contrastive training to reduce false positives in process reward models, improving step-level verification precision for reasoning LLMs.