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)

3,721 to 3,780 of 11,333

GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation
Arka Mukherjee, Soham Roy, Kartikeya Trivedi +1
cs.CVcs.CLarXiv:2608.29483v12026
Agentic Large Language Models, a survey
Aske Plaat, Max van Duijn, Niki van Stein +3
cs.AIcs.CLcs.LGarXiv:2503.23037v32025
Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
Vy Nguyen, Ziqi Xu, Jeffrey Chan +5
cs.CLcs.AIcs.LGarXiv:2608.28018v12026
TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements
Oktay Karakuş, Can Eyupoglu
cs.LGcs.CLarXiv:2608.26970v12026
Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models
Justin Bronder
cs.AIcs.CLarXiv:2608.27768v12026
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11
cs.PFcs.CLarXiv:2606.27457v12026
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
cs.CLarXiv:2601.03192v22026
Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference
Wooje Park, Insu Lee, Minyoung Noh +4
cs.CLarXiv:2608.26574v12026
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Yue Wang, Qiuzhi Liu, Jiahao Xu +11
cs.CLarXiv:2501.18585v22025
PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants
Weimin Lyu, Chen Luo, Guangrui Li +9
cs.CLcs.AIarXiv:2608.26180v12026
On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Study
Aditya Pratap Singh
cs.CLcs.AIcs.LGarXiv:2608.26292v12026
Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs
Paarth Singh Rathore
cs.CLarXiv:2608.26123v12026
Learning Language Games through Interaction
Sida I. Wang, Percy Liang, Christopher D. Manning
cs.CLcs.AIarXiv:1606.02447v12016
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
Siyi Zhou, Yiquan Zhou, Yi He +4
cs.CLcs.AIcs.SDarXiv:2506.21619v22025
The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation
Barbara Plank
cs.CLcs.LGarXiv:2211.02570v12022
The Multilingual FrameNet Corpus
Beatrice Fiumanò, Nicolas Lazzari, Simone Paolo Ponzetto +1
cs.CLcs.AIarXiv:2608.23037v12026
Improving Few-Step Language Flows with Untied Self-Conditioning
Bocheng Li, Linli Xu
cs.CLcs.AIcs.LGarXiv:2608.22244v12026
RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
Lin Sun, Jiquan Wang, Kai Zhang +2
cs.CLcs.LGarXiv:2102.02967v12021
Scaling Unsupervised Word Alignment to Documents via Structural Constraints
Michelle Wastl, Jannis Vamvas, Rico Sennrich
cs.CLarXiv:2608.21023v12026
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
Adaku Uchendu, Zeyu Ma, Thai Le +2
cs.CLarXiv:2109.13296v12021
Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach
Ashish Sharma, Inna W. Lin, Adam S. Miner +2
cs.CLcs.SIarXiv:2101.07714v32021
Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
Aarik Gulaya
cs.CLcs.AIcs.HCarXiv:2605.28969v22026
Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1
cs.CLarXiv:2608.20647v12026
PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers
Ngoc Phan Phuoc Loc, Toan Huynh La Viet, Thanh Tran Khanh +8
cs.CLarXiv:2605.26730v22026
Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers
Matteo Cargnelutti, Catherine Brobston, Eben English +6
cs.CLcs.DLarXiv:2608.18972v12026
FastKernels: Benchmarking GPU Kernel Generation in Production
Gabriele Oliaro, Yichao Fu, May Jiang +5
cs.LGcs.AIcs.CLarXiv:2605.23215v12026
From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning
Zuocheng Ying, Yang Yang, Yumou Wu +6
cs.CLcs.AIcs.LGarXiv:2608.18581v12026
Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs
Shayan Shahrabi-Farahani, Dara Rahmati
cs.CLcs.LGarXiv:2608.18578v12026
LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation
Venkata Pushpak Teja Menta
cs.SDcs.CLeess.ASarXiv:2605.00777v12026
Syntactic Data Augmentation Increases Robustness to Inference Heuristics
Junghyun Min, R. Thomas McCoy, Dipanjan Das +2
cs.CLarXiv:2004.11999v12020
HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents
Qianchu Liu, Sheng Zhang, Guanghui Qin +16
cs.AIcs.CLcs.CVarXiv:2606.31179v12026
Summaries:한국어
Scaling Long-Horizon LLM Agent via Context-Folding
Weiwei Sun, Miao Lu, Zhan Ling +4
cs.CLcs.LGarXiv:2510.11967v12025
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
cs.CVcs.CLarXiv:2603.27538v12026
Frames2LoRA: Parametric Video Internalization for Vision-Language Models
Manan Suri, Sarvesh Baskar, Dinesh Manocha
cs.CVcs.CLarXiv:2606.04351v22026
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf
Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner +17
cs.CLarXiv:2606.08857v12026
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates
Paiheng Xu, Jing Liu, Wei Ai
cs.CLcs.AIarXiv:2606.03029v12026
Model-Based Quality Assessment for Massively Multilingual Parallel Data
Abdelaziz M. A. Ibrahim, Zihao Li, Jörg Tiedemann +1
cs.CLarXiv:2606.00285v12026
CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations
Mike Zhang, Ali Basirat, Desmond Elliott
cs.CLcs.AIarXiv:2605.26293v12026
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
Dingbang Wu, Rui Hao, Haiyang Wang +8
cs.AIcs.CLarXiv:2605.26114v22026
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
Haolin Chen, Deon Metelski, Leon Qi +30
cs.CLcs.AIarXiv:2605.16679v22026
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
Qihang Fan, Huaibo Huang, Zhiying Wu +2
cs.CLarXiv:2605.06221v12026
LightMem: Lightweight and Efficient Memory-Augmented Generation
Jizhan Fang, Xinle Deng, Haoming Xu +9
cs.CLcs.AIcs.CVarXiv:2510.18866v42025
Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation
Lester James V. Miranda, Ivan Vulić, Anna Korhonen
cs.CLarXiv:2604.11290v22026
Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3
Natapong Nitarach
cs.CLarXiv:2603.27844v22026
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
Jack Young
cs.CLcs.LGarXiv:2604.01168v22026
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
Isha Puri, Mehul Damani, Idan Shenfeld +3
cs.LGcs.AIcs.CLarXiv:2603.24844v12026
Memento-Skills: Let Agents Design Agents
Huichi Zhou, Siyuan Guo, Anjie Liu +14
cs.AIcs.CLcs.LGarXiv:2603.18743v12026
Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
Sophie Kearney, Shu Yang, Zixuan Wen +8
cs.CLcs.LGq-bio.QMarXiv:2603.17191v12026
Unified Vision-Language Modeling via Concept Space Alignment
Yifu Qiu, Paul-Ambroise Duquenne, Holger Schwenk
cs.CVcs.AIcs.CLarXiv:2603.01096v12026
CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era
Kaiwen Shi, Weixiang Sun, Zheyuan Zhang +3
cs.CLcs.DLarXiv:2602.23452v32026
References Improve LLM Alignment in Non-Verifiable Domains
Kejian Shi, Yixin Liu, Peifeng Wang +3
cs.CLcs.AIcs.LGarXiv:2602.16802v12026
s1: Simple test-time scaling
Niklas Muennighoff, Zitong Yang, Weijia Shi +7
cs.CLcs.AIcs.LGarXiv:2501.19393v32025
Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding
Yuling Shi, Chaoxiang Xie, Zhensu Sun +7
cs.CLcs.SEarXiv:2602.01785v32026
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Chengyi Yang, Zhishang Xiang, Yunbo Tang +5
cs.LGcs.AIcs.CLarXiv:2601.22628v12026
AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
Shicheng Fang, Yuxin Wang, Xiaoran Liu +6
cs.CLarXiv:2601.20730v32026
REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Zafir Stojanovski, Oliver Stanley, Joe Sharratt +4
cs.LGcs.AIcs.CLarXiv:2505.24760v22025
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
Yao Tang, Li Dong, Yaru Hao +3
cs.CLcs.AIcs.LGarXiv:2601.08808v12026
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning
Tanyu Chen, Tairan Chen, Kai Shen +4
cs.SDcs.CLeess.ASarXiv:2601.11141v12026
SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers
Iaroslav Chelombitko, Ekaterina Chelombitko, Aleksey Komissarov
cs.CLcs.IRcs.LGarXiv:2601.04469v12026
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
Kunlun Zhu, Hongyi Du, Zhaochen Hong +8
cs.MAcs.AIcs.CLarXiv:2503.01935v12025

Computation and Language

GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation

Agentic Large Language Models, a survey

Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements

Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants

On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Study

Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs

Learning Language Games through Interaction

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation

The Multilingual FrameNet Corpus

Improving Few-Step Language Flows with Untied Self-Conditioning

RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER

Scaling Unsupervised Word Alignment to Documents via Structural Constraints

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation

Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach

Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization

Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails

PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers

Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers

FastKernels: Benchmarking GPU Kernel Generation in Production

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs

LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation

Syntactic Data Augmentation Increases Robustness to Inference Heuristics

HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents

Scaling Long-Horizon LLM Agent via Context-Folding

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Frames2LoRA: Parametric Video Internalization for Vision-Language Models

PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf

Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates

Model-Based Quality Assessment for Massively Multilingual Parallel Data

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

LightMem: Lightweight and Efficient Memory-Augmented Generation

Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation

Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

Memento-Skills: Let Agents Design Agents

Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data

Unified Vision-Language Modeling via Concept Space Alignment

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

References Improve LLM Alignment in Non-Verifiable Domains

s1: Simple test-time scaling

Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning

SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents