Artificial Intelligence

Papers filed under cs.AI on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

13,261 to 13,320 of 15,365

Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Xiangxiang Chu, Zhi Tian, Yuqing Wang +5
cs.CVcs.AIcs.LGarXiv:2104.13840v42021
Quantifying Attention Flow in Transformers
Samira Abnar, Willem Zuidema
cs.LGcs.AIcs.CLarXiv:2005.00928v22020
The Option-Critic Architecture
Pierre-Luc Bacon, Jean Harb, Doina Precup
cs.AIarXiv:1609.05140v22016
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
Noam Shazeer, Mitchell Stern
cs.LGcs.AIstat.MLarXiv:1804.04235v12018
Fast Byte Latent Transformer
Julie Kallini, Artidoro Pagnoni, Tomasz Limisiewicz +5
cs.CLcs.AIcs.LGarXiv:2605.08044v12026
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo +1
cs.CVcs.AIcs.LGarXiv:2104.13921v32021
code2vec: Learning Distributed Representations of Code
Uri Alon, Meital Zilberstein, Omer Levy +1
cs.LGcs.AIcs.PLarXiv:1803.09473v52018
Do not copy and paste! Rewriting strategies for code retrieval
Andrea Gurioli, Federico Pennino, Maurizio Gabbrielli
cs.SEcs.AIarXiv:2605.08299v12026
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
Zhe Liu, Zonghao Ying, Wenxin Zhang +5
cs.CRcs.AIarXiv:2605.05704v32026
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +3
cs.LGcs.AIcs.CLarXiv:2605.07924v12026
Analyzing Federated Learning through an Adversarial Lens
Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal +1
cs.LGcs.AIcs.CRarXiv:1811.12470v42018
Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages
Siqi Zhu
cs.AIcs.CYarXiv:2605.05558v22026
MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
Weihao Yu, Zhengyuan Yang, Linjie Li +5
cs.AIcs.CLcs.CVarXiv:2308.02490v42023
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
Hao Wang, Yiqun Sun, Pengfei Wei +2
cs.CVcs.AIcs.CLarXiv:2605.07447v12026
BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
Shaokai Ye, Vasileios Saveris, Yihao Qian +3
cs.CVcs.AIarXiv:2605.07394v12026
Implicit Preference Alignment for Human Image Animation
Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng +5
cs.CVcs.AIarXiv:2605.07545v12026
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
Salim Khazem, Ibrahim Mohamed Serouis, Zakaria Ezzahed
cs.CVcs.AIcs.LGarXiv:2605.08557v12026
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Kenneth Li, Oam Patel, Fernanda Viégas +2
cs.LGcs.AIcs.CLarXiv:2306.03341v62023
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
Jiahao Chen, Letian Gao, Yanhao Zhu +4
cs.AIarXiv:2605.08767v22026
Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
Ankit Hemant Lade, Sai Krishna Jasti, Indar Kumar +1
cs.LGcs.AIarXiv:2605.09169v22026
The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems
Robert Krajewski, Julian Bock, Laurent Kloeker +1
cs.CVcs.AIcs.IRarXiv:1810.05642v12018
Towards Accurate Generative Models of Video: A New Metric & Challenges
Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach +3
cs.CVcs.AIcs.LGarXiv:1812.01717v22018
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Yutszyuk Wong, Wentai Wu, Yuen-Ying Yeung +1
cs.LGcs.AIarXiv:2605.10988v12026
Learning Multiagent Communication with Backpropagation
Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
cs.LGcs.AIarXiv:1605.07736v22016
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
Alex Mallen, Akari Asai, Victor Zhong +3
cs.CLcs.AIcs.LGarXiv:2212.10511v42022
Capabilities of GPT-4 on Medical Challenge Problems
Harsha Nori, Nicholas King, Scott Mayer McKinney +2
cs.CLcs.AIarXiv:2303.13375v22023
RigidFormer: Learning Rigid Dynamics using Transformers
Zhiyang Dou, Minghao Guo, Haixu Wu +3
cs.CVcs.AIcs.GRarXiv:2605.09196v12026
DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules
Devin Yasith De Silva, Dhaval Patel, Christodoulos Constantinides +7
cs.AIarXiv:2605.08614v12026
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Aixin Liu, Bei Feng +154
cs.CLcs.AIarXiv:2405.04434v52024
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
Kun Xiang, Terry Jingchen Zhang, Zirong Liu +15
cs.AIarXiv:2605.09266v22026
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
Adrien Bardes, Jean Ponce, Yann LeCun
cs.CVcs.AIcs.LGarXiv:2105.04906v32021
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
Songtao Wei, Yi Li, Zhikai Li +7
cs.LGcs.AIarXiv:2605.09806v12026
A Review on Deep Learning Techniques Applied to Semantic Segmentation
Alberto Garcia-Garcia, Sergio Orts-Escolano, Sergiu Oprea +2
cs.CVcs.AIarXiv:1704.06857v12017
LIMA: Less Is More for Alignment
Chunting Zhou, Pengfei Liu, Puxin Xu +12
cs.CLcs.AIcs.LGarXiv:2305.11206v12023
Taskonomy: Disentangling Task Transfer Learning
Amir Zamir, Alexander Sax, William Shen +3
cs.CVcs.AIcs.LGarXiv:1804.08328v12018
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
Chia-Wei Liu, Ryan Lowe, Iulian V. Serban +3
cs.CLcs.AIcs.LGarXiv:1603.08023v22016
MetaFormer Is Actually What You Need for Vision
Weihao Yu, Mi Luo, Pan Zhou +5
cs.CVcs.AIcs.LGarXiv:2111.11418v32021
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Ben Shneiderman
cs.HCcs.AIarXiv:2002.04087v22020
Deep Learning in Spiking Neural Networks
Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh +2
cs.NEcs.AIarXiv:1804.08150v42018
Stacked Cross Attention for Image-Text Matching
Kuang-Huei Lee, Xi Chen, Gang Hua +2
cs.CVcs.AIcs.LGarXiv:1803.08024v22018
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Di Jin, Zhijing Jin, Joey Tianyi Zhou +1
cs.CLcs.AIcs.LGarXiv:1907.11932v62019
A Literature Survey of Benchmark Functions For Global Optimization Problems
Momin Jamil, Xin-She Yang
cs.AImath.OCarXiv:1308.4008v12013
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
Baibei Ji, Xiaoyang Weng, Juntao Li +3
cs.CLcs.AIarXiv:2605.10268v12026
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
Haoyu Huang, Jiaxin Bai, Shujie Liu +6
cs.CLcs.AIarXiv:2605.10488v12026
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Wenhu Chen, Xueguang Ma, Xinyi Wang +1
cs.CLcs.AIarXiv:2211.12588v42022
VideoBERT: A Joint Model for Video and Language Representation Learning
Chen Sun, Austin Myers, Carl Vondrick +2
cs.CVcs.AIarXiv:1904.01766v22019
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
Haokun Liu, Derek Tam, Mohammed Muqeeth +4
cs.LGcs.AIcs.CLarXiv:2205.05638v22022
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
George Wu, Nan Jing, Qing Yi +7
cs.AIarXiv:2605.10344v22026
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
Vincent Sitzmann, Michael Zollhöfer, Gordon Wetzstein
cs.CVcs.AIarXiv:1906.01618v22019
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
Daniel Goldstein, Navneel Singhal, Eugene Cheah
cs.LGcs.AIcs.CLarXiv:2605.09877v52026
Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
Zheyu Zhang, Shuo Yang, Bardh Prenkaj +1
cs.LGcs.AIarXiv:2605.10315v12026
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
Lezhong Wang, Mehmet Onurcan Kaya, Siavash Bigdeli +1
cs.CVcs.AIcs.GRarXiv:2605.11696v12026
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Runhui Huang, Jie Wu, Rui Yang +2
cs.CVcs.AIcs.LGarXiv:2605.12495v12026
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary +14
cs.AIcs.CLcs.LGarXiv:2605.12178v12026
CoQA: A Conversational Question Answering Challenge
Siva Reddy, Danqi Chen, Christopher D. Manning
cs.CLcs.AIcs.LGarXiv:1808.07042v22018
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
Valeriy Vyaltsev, Alsu Sagirova, Anton Andreychuk +5
cs.AIcs.LGcs.MAarXiv:2605.07637v22026
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
Eilam Shapira, Moshe Tennenholtz, Roi Reichart
cs.LGcs.AIcs.CLarXiv:2605.12411v12026
Debiased Model-based Representations for Sample-efficient Continuous Control
Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5
cs.LGcs.AIarXiv:2605.11711v12026
AST: Audio Spectrogram Transformer
Yuan Gong, Yu-An Chung, James Glass
cs.SDcs.AIarXiv:2104.01778v32021
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
Xuanyu Zhu, Yan Bai, Yang Shi +4
cs.CVcs.AIarXiv:2605.10780v22026

Artificial Intelligence

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Quantifying Attention Flow in Transformers

The Option-Critic Architecture

Adafactor: Adaptive Learning Rates with Sublinear Memory Cost

Fast Byte Latent Transformer

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

code2vec: Learning Distributed Representations of Code

Do not copy and paste! Rewriting strategies for code retrieval

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Analyzing Federated Learning through an Adversarial Lens

Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning

Implicit Preference Alignment for Human Image Animation

MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

From Holo Pockets to Electron Density: GPT-style Drug Design with Density

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems

Towards Accurate Generative Models of Video: A New Metric & Challenges

Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation

Learning Multiagent Communication with Backpropagation

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Capabilities of GPT-4 on Medical Challenge Problems

RigidFormer: Learning Rigid Dynamics using Transformers

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

A Review on Deep Learning Techniques Applied to Semantic Segmentation

LIMA: Less Is More for Alignment

Taskonomy: Disentangling Task Transfer Learning

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

MetaFormer Is Actually What You Need for Vision

Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy

Deep Learning in Spiking Neural Networks

Stacked Cross Attention for Image-Text Matching

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

A Literature Survey of Benchmark Functions For Global Optimization Problems

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

VideoBERT: A Joint Model for Video and Language Representation Learning

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

CoQA: A Conversational Question Answering Challenge

Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling

Debiased Model-based Representations for Sample-efficient Continuous Control

AST: Audio Spectrogram Transformer

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization