AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 26785 papers — Page 289 of 536
When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections
Sep 26, 2026
4 authors
cs.IRcs.LG
When Helpful Text Hurts: Option-Redirecting Bias in Vision-Language Models
Sep 26, 2026
4 authors
cs.AIcs.CV
RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems
Sep 26, 2026
5 authors
cs.AI
Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs
Sep 26, 2026
4 authors
cs.CLcs.AI
Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
Sep 26, 2026
5 authors
cs.AI
Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?
Sep 26, 2026
8 authors
cs.CRcs.AIcs.CE+1
Locally Sound, Globally Insufficient: The Local-Global Gap in Multi-Hop Reasoning
Sep 26, 2026
7 authors
cs.CL
Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models
Sep 26, 2026
5 authors
cs.CLcs.AI
TreeRef-BFN: Equivariance-Free De Novo Molecule Generation based on 2D Topology and Internal 3D Geometry
Sep 26, 2026
6 authors
cs.AIcs.LG
Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
Sep 26, 2026
2 authors
cs.LG
GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations
Sep 26, 2026
2 authors
cs.CV
Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents
Sep 26, 2026
7 authors
cs.AI
What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response
Sep 26, 2026
3 authors
cs.LGeess.SY
Cross-Domain Few-Shot Writer Adaptation for Real-World Handwritten Mathematical Expression Recognition
Sep 26, 2026
3 authors
cs.CV
From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis
Sep 26, 2026
10 authors
cs.AI
REFINE: A Resilient Evolution Framework for Intelligent Enterprise Alert Triage in Security Operations Centers
Sep 26, 2026
3 authors
cs.CRcs.AIcs.LG
UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation
Sep 26, 2026
7 authors
cs.CV
STR: Supervised Transcoder Replacement for Reducing Steering Side Effects
Sep 26, 2026
5 authors
cs.AIcs.LG
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Sep 26, 2026
4 authors
cs.CLcs.AI
MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents
Sep 26, 2026
8 authors
cs.AI
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
Sep 26, 2026
8 authors
cs.AIcs.IRcs.SD+1
AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses
Sep 26, 2026
5 authors
cs.AIcs.LGq-bio.GN+1
SetOPD: From Few Visual Exemplars to Multimodal Candidate Sets for Remote-Sensing Open-Prompt Detection
Sep 26, 2026
5 authors
cs.CV
What Does a ProcGen Generalization Gap Measure? Action Rules, Convergence, and the Missing Random Floor
Sep 26, 2026
1 authors
cs.LGcs.AI
LLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses
Sep 26, 2026
17 authors
cs.AI
DepthBench: Measuring How Residual Connections Enable More Computational Depth
Sep 26, 2026
6 authors
cs.CVcs.AIcs.LG
Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents
Sep 26, 2026
3 authors
cs.SDcs.AIcs.CL+2
RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision
Sep 26, 2026
3 authors
cs.CVcs.NE
Interpretable Physics Informed WiFi Indoor Localization: Learning an Effective Access Point Geometry and Using It to Prune
Sep 26, 2026
3 authors
cs.AIcs.LG
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
Sep 26, 2026
12 authors
cs.CVcs.AIcs.LG+1
Porimon: An LLM-Based Pokémon Battle Agent Enhanced by Long/Short-Term Knowledge Augmented Generation
Sep 26, 2026
4 authors
cs.AI
Shared Autoregressive Context Can Distort Relationships in Synthetic Data
Sep 26, 2026
1 authors
cs.LGcs.CL
Are Vision-Language-Action Models Robust to One-Step Observation Perturbations?
Sep 26, 2026
2 authors
cs.AIcs.LGcs.RO
Harnessing Coupled Stream Completion For Human-Object Interaction Modeling
Sep 26, 2026
3 authors
cs.CVcs.AI
Language as an Independent Information Layer: A Conceptual Model of Communication, Cognition and Decision-Making
Sep 26, 2026
2 authors
cs.CLcs.CEcs.CY+1