AI Research Papers — Page 55

AI News →Multi-source stories →Browse by company →

Archive, newest first. Filter by topic, impact and company →

Notableresearch

The Abstraction Gap in Vision-Language Causal Reasoning

May 27, 2026arXiv codeChinh Hoang +1

Notableresearch

Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?

May 27, 2026arXiv codeGabrielle Kaili-May Liu +1

Notableresearch

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

May 27, 2026arXiv codeSuji Kim +2

Notableresearch

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

May 27, 2026arXiv codeMinki Kang +5

Majorresearch

Rethinking Memory as Continuously Evolving Connectivity

May 27, 2026arXiv codeJizhan Fang +5

Notableresearch

Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations

May 27, 2026arXiv codeKevin Y. Li +3

Notableresearch

Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning

May 27, 2026arXiv codeMehryar Mohri +1

Majorresearch

SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks

May 27, 2026arXiv codeEdwin Jose

Notableresearch

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

May 27, 2026arXiv codeYiheng Zhu +5

NotableresearchIBM

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM

May 27, 2026

Notableresearch

LLM Zeroth-Order Fine-Tuning is an Inference Workload

May 27, 2026arXiv codeZelin Li +1

Notableresearch

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

May 27, 2026arXiv codeKunhao Zheng +5

Notableresearch

Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity

May 27, 2026arXiv codeMichael T. M. Emmerich

NotableresearchAnthropic

Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context

May 27, 2026arXiv codeThomas Mbrice

Notableresearch

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

May 27, 2026arXiv codeLinas Nasvytis +5

Notableresearch

Self-Prophetic Decoding to Unlock Visual Search in LVLMs

May 27, 2026arXiv codeZhendong He +4

Notableresearch

Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text

May 27, 2026arXiv codeBushi Xiao +2

Notableresearch

BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks

May 27, 2026arXiv codeTirtharaj Dash

Notableresearch

SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping

May 27, 2026arXiv codeHongyu Wen +1

Majorresearch

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

May 27, 2026arXiv codeRichard J. Young +1

Majorresearch

Utility-Aware Multimodal Contrastive Learning for Product Image Generation

May 27, 2026arXiv codeXiaohang Feng +1

Notableresearch

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

May 27, 2026arXiv codeXinle Deng +5

Notableresearch

AlphaTransit: Learning to Design City-scale Transit Routes

May 27, 2026arXiv codeBibek Poudel +2

Notableresearch

Beyond Lipschitz: Data-Driven Robustness via Discrete Modulus of Continuity

May 27, 2026arXiv codeJürgen Dölz +2

Notableresearch

How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures

May 27, 2026arXiv codeKrishnam Gupta

Majorresearch

Multi-Adapter Representation Interventions via Energy Calibration

May 27, 2026arXiv codeManjiang Yu +5

MajorresearchHugging Face

LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?

May 27, 2026arXiv codeHuiMing Fan +5

Notableresearch

OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol

May 27, 2026arXiv codeBojie Li

Notableresearch

IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents

May 27, 2026arXiv codeMichael Galarnyk +5

Notableresearch

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

May 27, 2026arXiv codeGuoxin Ma +5