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)

21,121 to 21,180 of 27,557

How broad is that claim? Mapping Generalisation in NLP Research
Chenxin Diao, Nataliya Stepanova, Emily Allaway
cs.CLcs.AIarXiv:2609.14770v22026
From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation
Xingjian Wang, Zhao Wang, Taihang Hu +14
cs.CVcs.AIarXiv:2608.18076v12026
CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models
Aaron Foss, Chloe Evans, Sasha Mitts +3
cs.CVcs.AIarXiv:2506.09943v12025
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Junzhe Li, Yutao Cui, Tao Huang +8
cs.AIcs.CVarXiv:2507.21802v72025
Does Muon Need Fine-Grained Spectral Shaping?
Meher Chaitanya, Tianyi Zhou, Aristides Gionis
cs.AIcs.LGstat.MLarXiv:2610.07497v12026
When More is Less: Understanding Chain-of-Thought Length in LLMs
Yuyang Wu, Yifei Wang, Ziyu Ye +3
cs.AIcs.CLcs.LGarXiv:2502.07266v32025
On the loss landscape of a class of deep neural networks with no bad local valleys
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
cs.LGcs.AIcs.CVarXiv:1809.10749v22018
Bayesian Intelligence from the Outside
Alex Smolin, Bryan Wilder
cs.AIecon.THarXiv:2609.14724v12026
PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
Zheng Zhao, Clara Vania, Subhradeep Kayal +3
cs.CLcs.AIcs.LGarXiv:2506.09902v12025
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
Shangge Liu, Yuehan Yin, Lei Wang +5
cs.AIarXiv:2604.17078v12026
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Xucong Wang, Ziyu Ma, Shidong Yang +4
cs.AIarXiv:2606.10917v22026
AIRGuard: Guarding Agent Actions with Runtime Authority Control
Suliu Qin, Haomin Zhuang, Yujun Zhou +2
cs.CRcs.AIarXiv:2605.28914v12026
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
Yecheng Wu, Song Han, Han Cai
cs.AIarXiv:2609.14708v22026
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
cs.AIcs.CCcs.CLarXiv:2601.18491v22026
Entity-level Factual Consistency of Abstractive Text Summarization
Feng Nan, Ramesh Nallapati, Zhiguo Wang +5
cs.CLcs.AIarXiv:2102.09130v12021
Skill Composition for Legged Robot Reinforcement Learning
Daniel Gigliotti, Flavio Maiorana, Fabio Patrizi +1
cs.ROcs.AIarXiv:2609.14647v12026
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
Jiawei Wang, Renhe Jiang, Chuang Yang +5
cs.AIcs.CLcs.CYarXiv:2402.14744v32024
Diffusion-Based Generation of Gait Trajectories
Damian Benasco, Juan Carballeira-Lopez, Jaime Ramos-Rojas +4
cs.AIcs.LGcs.ROarXiv:2609.14642v12026
All are Worth Words: A ViT Backbone for Diffusion Models
Fan Bao, Shen Nie, Kaiwen Xue +4
cs.CVcs.AIcs.LGarXiv:2209.12152v42022
Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation
Wenxuan Wang, Zekai Liu, Weinan Zhang +2
cs.AIarXiv:2610.07250v12026
AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory
Sushan Adhikari
cs.CYcs.AIcs.IRarXiv:2609.14572v12026
Can We Predict Before Executing Machine Learning Agents?
Jingsheng Zheng, Jintian Zhang, Yujie Luo +5
cs.CLcs.AIcs.LGarXiv:2601.05930v22026
A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration
Oleg Grynets, Oleg Kaskun, Alona Seletska +2
cs.LOcs.AIcs.MAarXiv:2609.14413v12026
CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering
Kunjesh Parekh, Anil Kumar Tiwari, Divya Saxena
cs.AIcs.CLq-fin.CParXiv:2608.26114v12026
Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Xinran Li, Chenjia Bai, Zijian Li +3
cs.MAcs.AIcs.LGarXiv:2506.07232v12025
Towards Zero-Shot Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension
Siamak Shakeri, Noah Constant, Mihir Sanjay Kale +1
cs.CLcs.AIcs.LGarXiv:2010.12008v32020
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
Tong Xiao, Xin Xu, Zhenya Huang +4
cs.LGcs.AIcs.CVarXiv:2506.07218v32025
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang +2
cs.CVcs.AIcs.LGarXiv:1607.03516v22016
ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution
Yee Man Choi, Xuehang Guo, Songcheng Cai +3
cs.DLcs.AIarXiv:2609.14248v12026
Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control
Sergei, Komarov
cs.LGcs.AIarXiv:2609.14234v12026
Contextual Experience Replay for Self-Improvement of Language Agents
Yitao Liu, Chenglei Si, Karthik Narasimhan +1
cs.AIcs.CLcs.CVarXiv:2506.06698v12025
ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution
Baixi Sun, Mingze Xia, Huihuo Zheng
cs.DCcs.AIarXiv:2609.14211v12026
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
Enneng Yang, Li Shen, Guibing Guo +4
cs.LGcs.AIcs.CLarXiv:2408.07666v52024
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
Zhiqiang Shen, Zechun Liu, Jie Qin +3
cs.CVcs.AIcs.LGarXiv:2102.08946v22021
Signatures of Steerability in Activation Space of Language Models
Prajjwal Bhattarai, Tuka Alhanai
cs.LGcs.AIarXiv:2609.14151v12026
Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
Madhura Joshi, Ankit Pal, Malaikannan Sankarasubbu
cs.LGcs.AIcs.CRarXiv:2211.07893v22022
Distributionally Robust Mixture-of-Experts Training
Xin Teng, Muxiao Li, Hongyi Wen
cs.LGcs.AIarXiv:2610.07207v12026
GLIGEN: Open-Set Grounded Text-to-Image Generation
Yuheng Li, Haotian Liu, Qingyang Wu +5
cs.CVcs.AIcs.CLarXiv:2301.07093v22023
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models
Kunwei Wu, Xiang Liu, Guocai Yao +5
cs.CVcs.AIcs.ROarXiv:2609.14073v22026
Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
Julian Minder, Clément Dumas, Caden Juang +2
cs.LGcs.AIcs.CLarXiv:2504.02922v42025
Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
Violet Xiang, Chase Blagden, Rafael Rafailov +4
cs.AIcs.LGarXiv:2506.05256v22025
Per-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity
Romain Claret, Michael O'Neill, Paul Cotofrei +1
cs.NEcs.AIarXiv:2610.00149v12026
Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments
Deepak Kanneganti, Sajib Mistry, Sheik Mohammad Mostakim Fattah +3
cs.LGcs.AIarXiv:2608.18555v12026
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning
Zhongyu Wang
cs.CLcs.AIcs.CVarXiv:2609.14066v12026
Explaining Legal Concepts with Augmented Large Language Models (GPT-4)
Jaromir Savelka, Kevin D. Ashley, Morgan A. Gray +2
cs.CLcs.AIarXiv:2306.09525v22023
VITA: Towards Open-Source Interactive Omni Multimodal LLM
Chaoyou Fu, Haojia Lin, Zuwei Long +16
cs.CVcs.AIcs.CLarXiv:2408.05211v32024
Convergent Emergence of In-Context Learning Across Modalities
Nathan Breslow, Seungwook Han, Daniel Hyunsoo Lee +3
cs.AIarXiv:2609.14011v12026
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu +2
cs.AIcs.LGarXiv:2607.22098v12026
IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck
Huilin Deng, Hongchen Luo, Yue Zhu +8
cs.LGcs.AIarXiv:2601.05870v12026
SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding
Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan +1
cs.LGcs.AIarXiv:2610.07086v12026
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Bin Lin, Zongjian Li, Xinhua Cheng +9
cs.CVcs.AIcs.CLarXiv:2506.03147v42025
A Performance Study of LLM-Generated Code on Leetcode
Tristan Coignion, Clément Quinton, Romain Rouvoy
cs.SEcs.AIarXiv:2407.21579v12024
End-to-End Context Compression at Scale
Ang Li, Sean McLeish, Haozhe Chen +12
cs.CLcs.AIcs.LGarXiv:2606.09659v12026
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story
Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal +5
cs.CLcs.AIcs.LGarXiv:2511.15210v12025
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control
Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4
cs.CRcs.AIarXiv:2609.14003v12026
KAN or MLP: A Fairer Comparison
Runpeng Yu, Weihao Yu, Xinchao Wang
cs.LGcs.AIarXiv:2407.16674v22024
SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus
Ming Zhao, Wenhui Dong, Yang Zhang +23
cs.CVcs.AIarXiv:2510.03160v32025
Parameter Space Noise for Exploration
Matthias Plappert, Rein Houthooft, Prafulla Dhariwal +6
cs.LGcs.AIcs.NEarXiv:1706.01905v22017
Legged Locomotion in Challenging Terrains using Egocentric Vision
Ananye Agarwal, Ashish Kumar, Jitendra Malik +1
cs.ROcs.AIcs.CVarXiv:2211.07638v12022
Multigrid with rough coefficients and Multiresolution operator decomposition from Hierarchical Information Games
Houman Owhadi
math.NAcs.AImath.STarXiv:1503.03467v52015

Artificial Intelligence

How broad is that claim? Mapping Generalisation in NLP Research

From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation

CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Does Muon Need Fine-Grained Spectral Shaping?

When More is Less: Understanding Chain-of-Thought Length in LLMs

On the loss landscape of a class of deep neural networks with no bad local valleys

Bayesian Intelligence from the Outside

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants

Understanding and Enforcing Weight Disentanglement in Task Arithmetic

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

AIRGuard: Guarding Agent Actions with Runtime Authority Control

Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Entity-level Factual Consistency of Abstractive Text Summarization

Skill Composition for Legged Robot Reinforcement Learning

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

Diffusion-Based Generation of Gait Trajectories

All are Worth Words: A ViT Backbone for Diffusion Models

Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation

AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory

Can We Predict Before Executing Machine Learning Agents?

A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration

CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering

Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments

Towards Zero-Shot Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension

Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward

Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation

ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution

Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control

Contextual Experience Replay for Self-Improvement of Language Agents

ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

Signatures of Steerability in Activation Space of Language Models

Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges

Distributionally Robust Mixture-of-Experts Training

GLIGEN: Open-Set Grounded Text-to-Image Generation

LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

Per-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity

Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments

GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning

Explaining Legal Concepts with Augmented Large Language Models (GPT-4)

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Convergent Emergence of In-Context Learning Across Modalities

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck

SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding

UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

A Performance Study of LLM-Generated Code on Leetcode

End-to-End Context Compression at Scale

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

KAN or MLP: A Fairer Comparison

SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus

Parameter Space Noise for Exploration

Legged Locomotion in Challenging Terrains using Egocentric Vision

Multigrid with rough coefficients and Multiresolution operator decomposition from Hierarchical Information Games