AI Research Papers — Page 77

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

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

Notableresearch

Improving Multi-turn Dialogue Consistency with Self-Recall Thinking

May 14, 2026arXiv codeRenning Pang +5

Notableresearch

Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

May 14, 2026arXiv codeRongman Xu +5

Notableresearch

CoralLite: μCT Reconstruction of Coral Colonies from Individual Corallites

May 14, 2026arXiv codeJess Jones +4

Notableresearch

SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection

May 14, 2026arXiv codeBatuhan Arda Bekar +3

Notableresearch

From Data to Action: Accelerating Refinery Optimization with AI

May 14, 2026arXiv codeDániel Pfeifer +5

Notableresearch

Novel Dynamic Batch-Sensitive Adam Optimiser for Vehicular Accident Injury Severity Prediction

May 14, 2026arXiv codeDaniel Asare Kyei +5

Notableresearch

Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models

May 14, 2026arXiv codeLibin Zhu +3

Majorresearch

ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World

May 14, 2026arXiv codeZiyin Zhang +4

Notableresearch

Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets

May 14, 2026arXiv codeRafi Al Attrach +5

Notableresearch

Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs

May 14, 2026arXiv codeGuangyu Feng +3

Majorresearch

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models

May 14, 2026arXiv codeMukul Ranjan +3

Notableresearch

NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework

May 14, 2026arXiv codeAlessio Caviglia +4

Majorresearch

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

May 14, 2026arXiv codeQuanhao Li +5

Majorresearch

TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale

May 14, 2026arXiv codeAnurup Ganguli

Notableresearch

An Interpretable Latency Model for Speculative Decoding in LLM Serving

May 14, 2026arXiv codeLinghao Kong +5

NotableresearchOpenAI

Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems

May 14, 2026arXiv codeYuxin Guo +2

Notableresearch

SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning

May 14, 2026arXiv codeKiHyun Nam +4

Notableresearch

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

May 14, 2026arXiv codeWuyang Li +5

Notableresearch

Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use

May 14, 2026arXiv codeRenning Pang +5

Criticalresearch

Orchard: An Open-Source Agentic Modeling Framework

May 14, 2026arXiv codeBaolin Peng +5

Majorresearch

AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models

May 14, 2026arXiv codeVinicius Covas +1

Notableresearch

From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG

May 14, 2026arXiv codeGuanhua Chen +5

MajorresearchBaichuan

COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

May 14, 2026arXiv codeZihan Deng +2

Notableresearch

Small, Private Language Models as Teammates for Educational Assessment Design

May 14, 2026arXiv codeChris Davis Jaldi +5

Notableresearch

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance

May 14, 2026arXiv codeKai Yan +2

NotableresearchScale AI

The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale

May 14, 2026arXiv codePeter A. Jansen

Majorresearch

Quantifying and Mitigating Premature Closure in Frontier LLMs

May 14, 2026arXiv codeRebecca Handler +2

Notableresearch

Explainable Detection of Depression Status Shifts from User Digital Traces

May 14, 2026arXiv codeLoris Belcastro +4

Notableresearch

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing

May 14, 2026arXiv codeJie Jiang +1

Notableresearch

Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA

May 14, 2026arXiv codeGuanhua Chen +5