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)

10,681 to 10,740 of 11,263

Variable-Width Transformers
Zhaofeng Wu, Oliver Sieberling, Shawn Tan +3
cs.CLarXiv:2606.18246v12026
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3
cs.CLcs.IRarXiv:2606.18508v12026
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
Amirhossein Abaskohi, Issam H. Laradji, Peter West +1
cs.CLcs.IRarXiv:2606.18381v12026
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish
Tolga Şakar
cs.CLcs.AIarXiv:2606.18717v12026
Sumi: Open Uniform Diffusion Language Model from Scratch
Mengyu Ye, Keito Kudo, Wataru Ikeda +3
cs.CLcs.LGarXiv:2606.19005v12026
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
Yueyi Sun, Yuhao Wang, Jason Li +8
cs.CVcs.AIcs.CLarXiv:2606.19534v12026
HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization
Zhentao Tan, Wei Chen, Jingyi Shen +4
cs.CLarXiv:2606.20097v12026
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Jincheng Zhong, Weizhi Wang, Che Jiang +5
cs.CLcs.SEarXiv:2606.23654v12026
PhoneBuddy: Training Open Models for Agentic Phone Use
Zhengyang Tang, Xin Lai, Pengyuan Lyu +23
cs.CLcs.AIarXiv:2606.23049v22026
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Haoling Li, Kai Zheng, Jie Wu +4
cs.AIcs.CLcs.CVarXiv:2606.23543v12026
OpenBioRQ: Unsolved Biomedical Research Questions for Agents
Minbyul Jeong
cs.CLarXiv:2606.21959v12026
Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents
Patricio M. Vera
cs.CLcs.AIarXiv:2606.22207v12026
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8
cs.CLarXiv:2606.21906v12026
Interleaved Speech Language Models Latently Work In Text
Talia Sternberg, Gallil Maimon, Yossi Adi
cs.CLcs.LGcs.SDarXiv:2606.22473v12026
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Charbel El Feghali, Arkil Patel, Nicholas Meade +3
cs.CRcs.CLarXiv:2606.21638v12026
From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis
Klesti Hoxha, Olti Qirici
cs.CLarXiv:2608.17454v12026
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3
cs.CLcs.AIcs.IRarXiv:2606.21710v12026
BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language
Qizhi Pei, Zhimeng Zhou, Yi Duan +9
cs.CLcs.AIcs.LGarXiv:2606.22138v12026
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
cs.LGcs.AIcs.CLarXiv:2605.04077v12026
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Bobo Li, Rui Wu, Zibo Ji +5
cs.CLcs.AIcs.CYarXiv:2604.19548v12026
TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction
Chengye Wang, Lin Fu, Zexi Kuang +1
cs.CLarXiv:2604.22880v12026
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
Zhen Ye, Xu Tan, Aoxiong Yin +8
cs.CVcs.CLcs.MMarXiv:2604.23586v22026
Characterizing Narrative Content in Web-scale LLM Pretraining Data
Teagan Johnson, Elliott Ash, Andrew Piper +1
cs.CLarXiv:2606.19468v12026
Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval
Lihui Ding, Zihan Guo, Bingwei Lu +5
cs.CLcs.IRarXiv:2608.16071v12026
Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
Syeda Faiza Ahmed, Zien Sheikh Ali, Hunzalah Hassan Bhatti +2
cs.CLcs.AIcs.SDarXiv:2608.17605v12026
LLM-Derived Preference Judgments Are Not Self-Consistent
Matthew T. Ford, Francis Bahk, Jingjing Wang +4
cs.AIcs.CLarXiv:2608.17644v12026
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
Md. Faiyaz Abdullah Sayeedi
cs.CLarXiv:2608.17950v12026
Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It
Quang Minh Nguyen, Luis Frentzen Salim
cs.CLarXiv:2608.17809v12026
TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification
Neelesh Kumar Shukla, Debasmita Panda, Srutanik Bhaduri +2
cs.CLarXiv:2608.17795v12026
SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis
Shicheng Ma, Wenqian Cui, Irwin King
cs.CLcs.MMcs.SDarXiv:2608.17931v12026
Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation
Iryna Hartsock, Cesar Lam, Christopher Otteni +4
cs.CLarXiv:2608.18072v12026
Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees
Sher Badshah, Ali Emami, Hassan Sajjad
cs.CLarXiv:2608.17994v12026
When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era
Lotta Kiefer, Brisca Balthes, Christoph Leiter +3
cs.CLarXiv:2608.17979v12026
BayesPrompt: human readable prompts that make sense
Franky Kevin Nando Tezoh, Ali Hussaini Umar, Alessandro Laio +2
cs.CLarXiv:2608.17866v12026
From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector
Camilla Dalerci, Thilo Michael, Robin Schaefer +1
cs.CLarXiv:2608.17827v12026
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
Qinyuan Ye, Yu Li, Yada Pruksachatkun +2
cs.AIcs.CLcs.LGarXiv:2608.18066v12026
An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning
Rubén Balbastre, Juan Manuel Orduña, Mariano Pérez
cs.LGcs.CLarXiv:2608.17804v12026
Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses
Alona Strugatski, Licol Zeinfeld, Jason Cooper +3
cs.CLcs.AIcs.HCarXiv:2608.17810v12026
Efficient Pre-Training with Token Superposition
Bowen Peng, Théo Gigant, Jeffrey Quesnelle
cs.CLarXiv:2605.06546v22026
Heterogeneous Scientific Foundation Model Collaboration
Zihao Li, Jiaru Zou, Feihao Fang +6
cs.AIcs.CLcs.LGarXiv:2604.27351v12026
Synthetic Computers at Scale for Long-Horizon Productivity Simulation
Tao Ge, Baolin Peng, Hao Cheng +1
cs.AIcs.CLcs.LGarXiv:2604.28181v12026
MiA-Signature: Approximating Global Activation for Long-Context Understanding
Yuqing Li, Jiangnan Li, Mo Yu +3
cs.CLarXiv:2605.06416v12026
MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware
Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathore +3
cs.CVcs.CLarXiv:2605.05945v72026
RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing
Jingjun Xu, Hongji Pu, Tao Feng +3
cs.NIcs.CLarXiv:2605.00180v22026
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Peiyang Liu, Ziqiang Cui, Xi Wang +2
cs.CVcs.AIcs.CLarXiv:2605.01284v22026
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
cs.CLarXiv:2605.07243v22026
TextLDM: Language Modeling with Continuous Latent Diffusion
Jiaxiu Jiang, Jingjing Ren, Wenbo Li +10
cs.CLarXiv:2605.07748v12026
Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho +1
cs.LGcs.CLstat.MLarXiv:2605.08423v12026
Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
Zhengyang Tang, Yi Zhang, Chenxin Li +18
cs.CLcs.AIcs.LGarXiv:2605.07630v12026
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
Yoav Gur-Arieh, Ana Marasović, Mor Geva
cs.CLarXiv:2605.25052v12026
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Yujie Lin, Chengyi Yang, Zhishang Xiang +2
cs.LGcs.AIcs.CLarXiv:2605.18879v32026
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
Guanglong Sun, Siyuan Zhang, Liyuan Wang +3
cs.LGcs.CLarXiv:2602.07892v22026
Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL
Qizhen Lan, Xi Xiao, Xiangchen Guan +4
cs.AIcs.CLarXiv:2608.14945v12026
A Causal Language Modeling Detour Improves Encoder Continued Pretraining
Rian Touchent, Eric de la Clergerie
cs.CLcs.AIarXiv:2605.12438v12026
The Unlearnability Phenomenon in RLVR for Language Models
Yulin Chen, He He, Chen Zhao
cs.LGcs.CLarXiv:2605.16787v12026
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
Neha Verma, Nikhil Mehta, Shao-Chuan Wang +7
cs.CLcs.IRcs.LGarXiv:2605.12419v12026
PresentAgent-2: Towards Generalist Multimodal Presentation Agents
Wei Wu, Ziyang Xu, Zeyu Zhang +2
cs.CVcs.CLarXiv:2605.11363v12026
PreScam: A Benchmark for Predicting Scam Progression from Early Conversations
Weixiang Sun, Shang Ma, Yiyang Li +5
cs.CLarXiv:2605.12243v12026
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6
cs.LGcs.CLcs.CRarXiv:2605.14454v12026
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
Ziyu Guo, Rain Liu, Xinyan Chen +1
cs.CVcs.AIcs.CLarXiv:2605.15198v12026

Computation and Language

Variable-Width Transformers

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish

Sumi: Open Uniform Diffusion Language Model from Scratch

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

PhoneBuddy: Training Open Models for Agentic Phone Use

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

OpenBioRQ: Unsolved Biomedical Research Questions for Agents

Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Interleaved Speech Language Models Latently Work In Text

Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis

PrivacyAlign: Contextual Privacy Alignment for LLM Agents

BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment

TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction

Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling

Characterizing Narrative Content in Web-scale LLM Pretraining Data

Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval

Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

LLM-Derived Preference Judgments Are Not Self-Consistent

Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds

Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It

TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification

SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis

Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation

Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees

When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era

BayesPrompt: human readable prompts that make sense

From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector

On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification

An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning

Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses

Efficient Pre-Training with Token Superposition

Heterogeneous Scientific Foundation Model Collaboration

Synthetic Computers at Scale for Long-Horizon Productivity Simulation

MiA-Signature: Approximating Global Activation for Long-Context Understanding

MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware

RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting

TextLDM: Language Modeling with Continuous Latent Diffusion

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

The Unlearnability Phenomenon in RLVR for Language Models

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging

PresentAgent-2: Towards Generalist Multimodal Presentation Agents

PreScam: A Benchmark for Predicting Scam Progression from Early Conversations

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both