Computation and Language

Papers filed under cs.CL 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)

10,861 to 10,920 of 11,332

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models
Xiutian Zhao, Luqi Sun, Björn Schuller +1
cs.CLeess.ASeess.IVarXiv:2608.17102v12026
Effects of Answer Format Variation on Gender Bias in Large Language Models
Ksenia Merzlyakova, Sebastian Padó, Franziska Weeber
cs.CLarXiv:2608.17516v12026
An Investigation of Translationese in the Generations of Multilingual Large Language Models
Maria Valentini, Téa Wright, Julisa Granados +2
cs.CLarXiv:2608.17399v12026
Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention
Emama Nahid, Tahmid Imtiaz Imu, Huayue Gu +3
cs.CLarXiv:2608.17288v12026
What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?
Saketh Reddy Vemula, Parameswari Krishnamurthy
cs.CLarXiv:2608.17325v12026
PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX
Genghan Zhang, Yixin Dong, Chengze Fan +4
cs.CLcs.AIarXiv:2608.17379v12026
Summaries:简体中文
Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
Hamidreza Saffari, Francesco Pierri
cs.CLarXiv:2608.17583v12026
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Jiaqi Tang, Jianmin Chen, Youyang Zhai +6
cs.CVcs.AIcs.CLarXiv:2606.08063v12026
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
Yuting Ning, Zhehao Zhang, Yash Kumar Lal +8
cs.CLarXiv:2606.02540v12026
Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases
Cheng Liang, Pengcheng Qiu, Ya Zhang +3
cs.CLarXiv:2606.05112v12026
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Jingwen Chen, Wenkai Yang, Shengda Fan +7
cs.CLcs.LGarXiv:2606.04703v12026
Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle
Juan S. Santillana
cs.CLarXiv:2606.09376v22026
Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation
Cedric Caruzzo, Donggeun Yoo, Tae Soo Kim
cs.LGcs.AIcs.CLarXiv:2608.15787v12026
Large Language Models Are Overconfident in Their Own Responses
Mario Sanz-Guerrero, Manuel Mager, Katharina von der Wense
cs.CLarXiv:2606.03437v12026
Latent Reasoning with Normalizing Flows
Guancheng Tu, Xiangjun Fu, Suhao Yu +5
cs.CLcs.LGarXiv:2606.06447v12026
Re-Centering Humans in LLM Personalization
Lechen Zhang, Jiarui Liu, Tal August
cs.CLcs.AIcs.HCarXiv:2606.06614v12026
ICA Lens: Interpreting Language Models Without Training Another Dictionary
Sida Liu, Feijiang Han
cs.LGcs.AIcs.CLarXiv:2606.11722v12026
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
Sanjay Adhikesaven, Haoxiang Sun, Sewon Min
cs.CLarXiv:2606.12385v12026
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Hao Xiang, Qiaoyu Tang, Le Yu +8
cs.CLarXiv:2606.12373v12026
RedAct: Redacting Agent Capability Traces for Procedural Skill Protection
Shuwen Xu, Zhitao He, Yi R. Fung
cs.CRcs.CLarXiv:2606.10813v32026
TokenPilot: Cache-Efficient Context Management for LLM Agents
Buqiang Xu, Zirui Xue, Dianmou Chen +12
cs.CLcs.AIcs.LGarXiv:2606.17016v12026
Native Active Perception as Reasoning for Omni-Modal Understanding
Zhenghao Xing, Ruiyang Xu, Yuxuan Wang +8
cs.CVcs.CLcs.SDarXiv:2606.19341v22026
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
Zhichen Dong, Yang Li, Yuhan Sun +9
cs.LGcs.CLarXiv:2606.10646v12026
Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models
Changyue Wang, Weihang Su, Qingyao Ai +5
cs.CLarXiv:2606.12203v12026
Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics
Igor Itkin
cs.LGcs.AIcs.CLarXiv:2606.12476v32026
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Baochang Ren, Xinjie Liu, Xi Chen +15
cs.CLcs.AIcs.LGarXiv:2606.13578v22026
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning
Sicheng Yang, Hangjie Yuan, Wenjun Zhang +5
cs.CVcs.AIcs.CLarXiv:2606.14697v12026
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Sen Xu, Shixi Liu, Wei Wang +6
cs.AIcs.CLarXiv:2606.16140v12026
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Mingyang Li, Yurou Liu, Jieping Ye +3
cs.CLarXiv:2606.16905v12026
Looped World Models
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28
cs.LGcs.AIcs.CLarXiv:2606.18208v12026
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
Zhe Ren, Yibo Yang, Yimeng Chen +7
cs.LGcs.CLarXiv:2606.18829v12026
MAIC-UI: Making Interactive Courseware with Generative UI
Shangqing Tu, Yanjia Li, Keyu Chen +7
cs.CLcs.AIcs.HCarXiv:2604.25806v12026
Summaries:한국어
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
Jiayu Yang, Chao Chen, Shengen Wu +6
cs.LGcs.CLarXiv:2606.13106v12026
PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech
Venkata Pushpak Teja Menta
cs.SDcs.CLarXiv:2604.25476v12026
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
cs.CLcs.AIarXiv:2605.05662v12026
EMO: Pretraining Mixture of Experts for Emergent Modularity
Ryan Wang, Akshita Bhagia, Sewon Min
cs.CLarXiv:2605.06663v22026
A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
cs.CLarXiv:2605.06200v12026
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Nahyun Lee, Dongkeun Yoon, Guijin Son +12
cs.CLarXiv:2606.02404v12026
Dynamic Linear Attention
Xin Wang, Hui Shen, Boyuan Zheng +7
cs.CLcs.AIarXiv:2606.10650v12026
MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
Lawrence Keunho Jang, Andrew Keunwoo Jang, Jing Yu Koh +1
cs.LGcs.CLarXiv:2606.16748v12026
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Guy Kaplan, Zorik Gekhman, Zhen Zhu +5
cs.CLcs.AIcs.LGarXiv:2604.15574v12026
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Yuyang Li, Yime He, Zeyu Zhang +1
cs.CVcs.CLarXiv:2604.27695v12026
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Chengshuai Shi, Wenzhe Li, Xinran Liang +10
cs.LGcs.AIcs.CLarXiv:2605.00347v12026
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
Cheng Qian, Hyeonjeong Ha, Jiayu Liu +10
cs.AIcs.CLcs.LGarXiv:2605.02910v22026
When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
Jiaqi Wei, Xuehang Guo, Pengfei Yu +5
cs.CLarXiv:2605.03314v22026
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Xinjie Shen, Rongzhe Wei, Peizhi Niu +6
cs.CLcs.AIcs.CRarXiv:2605.05630v22026
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
Shengkun Tang, Zekun Wang, Bo Zheng +7
cs.LGcs.AIcs.CLarXiv:2605.08738v22026
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
Chuanyang Jin, Binze Li, Haopeng Xie +6
cs.CLcs.AIarXiv:2605.20087v22026
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Jingwei Sun, Jianing Zhu, Jiangchao Yao +2
cs.CLarXiv:2605.19952v12026
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Weimin Xiong, Shuhao Gu, Bowen Ye +5
cs.CLcs.AIcs.CVarXiv:2605.14747v12026
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
Wenjun Wang, Yanggan Gu, Shuo Cai +4
cs.CLarXiv:2605.16882v12026
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Théo Gigant, Bowen Peng, Jeffrey Quesnelle
cs.CLarXiv:2604.27263v22026
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
Haiquan Lu, Zigeng Chen, Gongfan Fang +2
cs.CLarXiv:2605.20315v12026
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
Guijin Son, Seungyeop Yi, Minju Gwak +3
cs.CLarXiv:2605.28003v12026
Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning
Ao Shen, Yongheng Zhang, Yinghui Li +3
cs.CVcs.AIcs.CLarXiv:2608.16316v12026
TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness
TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin +7
cs.CLarXiv:2608.15763v12026
SkillComposer: Learning Reusable Skills for Natural-Language Robot Programming
John Woods, Hasti Seifi
cs.ROcs.CLcs.LGarXiv:2608.14944v12026
Semantic Space of Parts of Speech
Jiří Milička, Ivan Kraus, Arnold Stanovský +5
cs.CLarXiv:2608.15443v12026
Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval
Prashant Kumar Pathak, Tarun Kumar Sharma
cs.CRcs.CLcs.IRarXiv:2608.16044v12026
DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech
Pengcheng Wang, Sheng Li, Jiyi Li +1
cs.CLeess.ASarXiv:2608.16053v12026

Computation and Language

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

Effects of Answer Format Variation on Gender Bias in Large Language Models

An Investigation of Translationese in the Generations of Multilingual Large Language Models

Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention

What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle

Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation

Large Language Models Are Overconfident in Their Own Responses

Latent Reasoning with Normalizing Flows

Re-Centering Humans in LLM Personalization

ICA Lens: Interpreting Language Models Without Training Another Dictionary

Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

RedAct: Redacting Agent Capability Traces for Procedural Skill Protection

TokenPilot: Cache-Efficient Context Management for LLM Agents

Native Active Perception as Reasoning for Omni-Modal Understanding

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences

Looped World Models

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

MAIC-UI: Making Interactive Courseware with Generative UI

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech

XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

EMO: Pretraining Mixture of Experts for Emergent Modularity

A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Dynamic Linear Attention

MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents

Why Fine-Tuning Encourages Hallucinations and How to Fix It

EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training

ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring

Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness

SkillComposer: Learning Reusable Skills for Natural-Language Robot Programming

Semantic Space of Parts of Speech

Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval

DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech