A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
The paper tests whether in-context learning learns label relationships by flipping label relations during ICL, finding it learns relationships but is not conventional learning.
Unknown
A reflective overview of how text indexing evolved from manual keyword lists to full-text search and modern large language models.
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.
Daman Arora, Andrea Zanette
This paper proposes using reinforcement learning to train large reasoning models to dynamically allocate inference-time compute based on task complexity, reducing inference costs while preserving accuracy.
Qi Sun, Edoardo Cetin, Yujin Tang
Transformer-Squared is a self-adaptive LLM framework that adjusts only the singular components of weight matrices in real-time, using a two-pass dispatch and reinforcement-learned expert vectors to outperform LoRA with fewer parameters.
Roeland Scheepens, Niels Willems, Huub van de Wetering, et al.
This paper introduces a flexible architecture for multivariate trajectory density maps using composable blocks and expressions, enabling analysts to model domain knowledge for visual exploration.
Yuanhe Zhang, Weiliu Wang, Jie Ren, et al.
Proposes ILL, an inaudible red teaming method using low-frequency waveforms to attack LALMs, and DRG, a defense that detects distribution shifts and requests reacquisition, reducing accuracy by up to 67 points.
Ebenezer Gelo, Geraud Nangue Tasse, Steven James, et al.
Proposes RCI framework to convert sparse trajectory-level stop-feedback into dense per-step costs for safe offline RL, preserving feasible policy set and optimal Lagrangian.
Bajaj, Payal, Campos, Daniel, Craswell, Nick, et al.
This paper presents a dataset for the Advertisement in Retrieval-Augmented Generation task at Touché 2025, using segments from MS MARCO V2.1 and queries from Webis Generated Native Ads 2024.
Daniel Armstrong, Xuan-Vu Nguyen, Octavian Susanu, et al.
SynthEx, an agentic LLM framework, plans retrosynthetic routes to complex natural products that expert chemists judge comparable to human-designed syntheses.
Unknown
The paper demonstrates that fine-tuning protein language models improves prediction performance across diverse protein-related tasks.
Unknown
This paper proposes parameter-efficient fine-tuning methods for protein language models to democratize their application, reducing computational costs while maintaining performance.