Academic

Academic · 1 min

CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

arXiv:2604.03374v1 Announce Type: new Abstract: Creative problem-solving requires combining multiple cognitive abilities, including logical reasoning, lateral thinking, analogy-making, and commonsense knowledge, to discover insights that …

Mete Ismayilzada, Renqing Cuomao, Daniil Yurshevich, Anna Sotnikova, Lonneke van der Plas, Antoine Bosselut

8 views Apr 7

Academic · 1 min

Knowledge Packs: Zero-Token Knowledge Delivery via KV Cache Injection

arXiv:2604.03270v1 Announce Type: new Abstract: RAG wastes tokens. We propose Knowledge Packs: pre-computed KV caches that deliver the same knowledge at zero token cost. For …

Andrey Pustovit

8 views Apr 7

Academic · 1 min

LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

arXiv:2604.03263v1 Announce Type: new Abstract: Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively …

Keqin Xie

17 views Apr 7

Academic · 1 min

VIGIL: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers

arXiv:2604.03261v1 Announce Type: new Abstract: The rise of generative AI is posing increasing risks to online information integrity and civic discourse. Most concretely, such risks …

Bo Kang, Sander Noels, Tijl De Bie

29 views Apr 7

Academic · 1 min

Why Attend to Everything? Focus is the Key

arXiv:2604.03260v1 Announce Type: new Abstract: We introduce Focus, a method that learns which token pairs matter rather than approximating all of them. Learnable centroids assign …

Hengshuai Yao, Xing Chen, Ahmed Murtadha, Jin Li, Shuai Shao, Yasin Abbasi Yadkori, Guan Wang, Mingli Yuan, William Chen, Sen Song

4 views Apr 7

Academic · 1 min

SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

arXiv:2604.03258v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing …

Xinhao Huang, You-Liang Huang, Zeyi Wen

9 views Apr 7

Academic · 1 min

Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation

arXiv:2604.03257v1 Announce Type: new Abstract: The ability to rigorously estimate the failure rates of large language models (LLMs) is a prerequisite for their safe deployment. …

Minghe Shen, Ananth Balashankar, Adam Fisch, David Madras, Miguel Rodrigues

7 views Apr 7

Academic · 1 min

Self-Execution Simulation Improves Coding Models

arXiv:2604.03253v1 Announce Type: new Abstract: A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program …

Gallil Maimon, Ori Yoran, Felix Kreuk, Michael Hassid, Gal Cohen, Pierre Chambon, Yossi Adi

7 views Apr 7

Academic · 1 min

Don't Blink: Evidence Collapse during Multimodal Reasoning

arXiv:2604.04207v1 Announce Type: new Abstract: Reasoning VLMs can become more accurate while progressively losing visual grounding as they think. This creates task-conditional danger zones where …

Suresh Raghu, Satwik Pandey

2 views Apr 7

Academic · 1 min

Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty

arXiv:2604.04182v1 Announce Type: new Abstract: Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as …

Haomiaomiao Wang, Tom\'as E Ward, Lili Zhang

2 views Apr 7

Academic · 1 min

CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection

arXiv:2604.04174v1 Announce Type: new Abstract: The proliferation of fake news across diverse domains highlights critical limitations in current detection systems, which often exhibit narrow domain …

Esma A\"imeur, Gilles Brassard, Dorsaf Sallami

2 views Apr 7

Academic · 1 min

A Model of Understanding in Deep Learning Systems

arXiv:2604.04171v1 Announce Type: new Abstract: I propose a model of systematic understanding, suitable for machine learning systems. On this account, an agent understands a property …

David Peter Wallis Freeborn

12 views Apr 7

CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

Knowledge Packs: Zero-Token Knowledge Delivery via KV Cache Injection

LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

VIGIL: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers

Why Attend to Everything? Focus is the Key

SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation

Self-Execution Simulation Improves Coding Models

Don't Blink: Evidence Collapse during Multimodal Reasoning

Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty

CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection

A Model of Understanding in Deep Learning Systems

JCG, PC

HSOLLC Co., Ltd.