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)

12,121 to 12,180 of 19,338

DataComp-VLM: Improved Open Datasets for Vision-Language Models
Matteo Farina, Vishaal Udandarao, Thao Nguyen +33
cs.CVcs.CLcs.LGarXiv:2606.28551v32026
Learning Joint Multilingual Sentence Representations with Neural Machine Translation
Holger Schwenk, Matthijs Douze
cs.CLarXiv:1704.04154v22017
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Zhao Yang, Jiaqi Wang, Yansong Tang +3
cs.CVcs.CLarXiv:2112.02244v22021
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Yurun Yuan, Tengyang Xie
cs.LGcs.AIcs.CLarXiv:2603.19987v12026
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer +4
cs.CLcs.AIcs.CVarXiv:2402.05602v22024
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
Pengrui Han, Xueqiang Xu, Keyang Xuan +12
cs.AIcs.CLcs.LGarXiv:2602.07276v12026
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Pengcheng Jiang, Zhiyi Shi, Kelly Hong +5
cs.AIcs.CLcs.IRarXiv:2606.02373v12026
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
Cunxiao Du, Jing Jiang, Xu Yuanchen +8
cs.CLarXiv:2402.02082v12024
FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
Ajay Patel, Colin Raffel, Chris Callison-Burch
cs.CLcs.LGarXiv:2601.22146v32026
Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
Katie Matton, Robert Osazuwa Ness, John Guttag +1
cs.CLcs.AIcs.LGarXiv:2504.14150v22025
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich +3
cs.CVcs.CLarXiv:2109.06129v22021
Pretrained Transformers for Text Ranking: BERT and Beyond
Jimmy Lin, Rodrigo Nogueira, Andrew Yates
cs.IRcs.CLarXiv:2010.06467v32020
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Yiwei Qin, Zhen Huang, Tiantian Mi +5
cs.AIcs.CLarXiv:2602.07824v12026
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +5
cs.CLarXiv:2607.00482v22026
Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Ananya B. Sai, Tanay Dixit, Dev Yashpal Sheth +2
cs.CLarXiv:2109.05771v12021
KV Cache Compression Through the Lens of Transform Coding
Hannah Laus, Claudio Mayrink Verdun, Hao Wang +2
cs.LGcs.CLeess.SParXiv:2608.14191v12026
Interactive Attention Networks for Aspect-Level Sentiment Classification
Dehong Ma, Sujian Li, Xiaodong Zhang +1
cs.AIcs.CLarXiv:1709.00893v12017
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
Houcheng Jiang, Boxuan Zhang, Qiyong Zhong +3
cs.AIcs.CLarXiv:2608.24275v12026
Multi-hop Reasoning via Early Knowledge Alignment
Yuxin Wang, Shicheng Fang, Bo Wang +4
cs.CLarXiv:2512.20144v22025
Demographic Dialectal Variation in Social Media: A Case Study of African-American English
Su Lin Blodgett, Lisa Green, Brendan O'Connor
cs.CLarXiv:1608.08868v12016
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +271
cs.CLarXiv:2504.13914v32025
Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
Yuchen Huang, Sijia Li, Jun Zhang +1
cs.AIcs.CLarXiv:2608.22963v12026
Uncovering Cross-Objective Interference in Multi-Objective Alignment
Yining Lu, Meng Jiang
cs.CLcs.LGarXiv:2602.06869v22026
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
Xin Wang, Yu Zheng, Zhongwei Wan +1
cs.CLcs.LGarXiv:2403.07378v52024
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
Zhiben Chen, Youpeng Zhao, Yang Sui +2
cs.CLarXiv:2605.20179v12026
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
cs.LGcs.AIcs.CLarXiv:2402.05162v42024
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Yushi Sun, Bowen Cao, Wai Lam
cs.DBcs.CLarXiv:2607.00394v12026
Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration
Kaicheng Xiao, Liran Dong, Haotian Li +1
cs.LGcs.CLarXiv:2610.11214v12026
Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng +6
cs.CLarXiv:2505.18454v22025
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Chih-Yao Ma, Jiasen Lu, Zuxuan Wu +4
cs.AIcs.CLcs.CVarXiv:1901.03035v12019
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
Yixuan Even Xu, Yash Savani, Fei Fang +1
cs.LGcs.AIcs.CLarXiv:2504.13818v52025
Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval
Linhai Ma, Ethan F. Wei, Xueqing Peng +3
cs.CLcs.AIarXiv:2608.06614v12026
Latent-Aligned Reasoning for Multimodal Recommendation
Jiarui Jin, Anyang Ji
cs.IRcs.CLcs.CVarXiv:2609.04645v12026
LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics
Yumeng Fu, Junjie Wu, Zhongjie Wang +4
cs.CLarXiv:2403.07260v22024
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
Qing Zong, Jiayu Liu, Tianshi Zheng +7
cs.CLarXiv:2510.24505v12025
Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Sercan Arik, Gregory Diamos, Andrew Gibiansky +5
cs.CLarXiv:1705.08947v22017
Universal Neural Machine Translation for Extremely Low Resource Languages
Jiatao Gu, Hany Hassan, Jacob Devlin +1
cs.CLarXiv:1802.05368v22018
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Yong Yi Bay, Kathleen A. Yearick
cs.LGcs.AIcs.CLarXiv:2607.00152v12026
Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
Haoyu Zhang, Zhipeng Li, Yiwen Guo +1
cs.CVcs.AIcs.CLarXiv:2602.07106v22026
FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection
Jinchang Zhu, Jindong Li, Yi Ding +5
cs.CLarXiv:2608.21750v12026
Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
Alireza Rezazadeh, Zichao Li, Ange Lou +3
cs.MAcs.AIcs.CLarXiv:2505.18279v12025
Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo +4
cs.CVcs.AIcs.CLarXiv:2505.18079v42025
SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers
Keyang Xuan, Pengda Wang, Chongrui Ye +3
cs.AIcs.CLarXiv:2602.05115v12026
Minimal Witness Reinforcement Learning
T. Y. Tsui, Zihao Ye, Pengxiang Cai +3
cs.LGcs.AIcs.CLarXiv:2610.07226v12026
Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models
Omer Luxembourg, Haim Permuter, Eliya Nachmani
cs.CLcs.AIcs.ITarXiv:2506.19037v52025
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
Andrej Leban, Yuekai Sun
cs.AIcs.CLcs.LGarXiv:2607.08093v12026
K-Bench: measuring model performance on real scientific agent requests
Aubrey Brueckner, Darshil Patel, Yuhuan He +1
cs.AIcs.CLarXiv:2608.21601v12026
A Storage-Retrieval Gap in Parametric Knowledge Graph Memory
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov +1
cs.LGcs.CLcs.IRarXiv:2608.25489v12026
Structured Denoising Diffusion Models in Discrete State-Spaces
Jacob Austin, Daniel D. Johnson, Jonathan Ho +2
cs.LGcs.AIcs.CLarXiv:2107.03006v32021
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
Christian Walder, Deep Karkhanis
cs.LGcs.AIcs.CLarXiv:2505.15201v52025
RexBERT: Context Specialized Bidirectional Encoders for E-commerce
Rahul Bajaj, Anuj Garg
cs.CLcs.AIarXiv:2602.04605v12026
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
Yifan Wang, Bolian Li, Junlin Wu +5
cs.CLcs.AIarXiv:2510.02341v22025
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Ziyi Lin, Chris Liu, Renrui Zhang +13
cs.CVcs.AIcs.CLarXiv:2311.07575v12023
Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text
Haoyuan Li, Snigdha Chaturvedi
cs.CLarXiv:2608.23783v12026
CoVoST 2 and Massively Multilingual Speech-to-Text Translation
Changhan Wang, Anne Wu, Juan Pino
cs.CLcs.SDeess.ASarXiv:2007.10310v32020
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
cs.LGcs.CLarXiv:2403.06988v12024
MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback
Wanhao Liu, Zonglin Yang, Jue Wang +7
cs.CLcs.AIcs.CEarXiv:2505.17873v32025
Efficient Neural Architecture Search via Parameter Sharing
Hieu Pham, Melody Y. Guan, Barret Zoph +2
cs.LGcs.CLcs.CVarXiv:1802.03268v22018
Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study
Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil +6
cs.CLarXiv:2608.25574v12026
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
Taejin Park, Ivan Medennikov, Kunal Dhawan +6
eess.AScs.CLcs.LGarXiv:2409.06656v32024

Computation and Language

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Learning Joint Multilingual Sentence Representations with Neural Machine Translation

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

Pretrained Transformers for Text Ranking: BERT and Beyond

Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training

Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

KV Cache Compression Through the Lens of Transform Coding

Interactive Attention Networks for Aspect-Level Sentiment Classification

RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards

Multi-hop Reasoning via Early Knowledge Alignment

Demographic Dialectal Variation in Social Media: A Case Study of African-American English

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

Uncovering Cross-Objective Interference in Multi-Objective Alignment

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers

Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration

Hybrid Latent Reasoning via Reinforcement Learning

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval

Latent-Aligned Reasoning for Multimodal Recommendation

LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

Deep Voice 2: Multi-Speaker Neural Text-to-Speech

Universal Neural Machine Translation for Extremely Low Resource Languages

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Minimal Witness Reinforcement Learning

Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

K-Bench: measuring model performance on real scientific agent requests

A Storage-Retrieval Gap in Parametric Knowledge Graph Memory

Structured Denoising Diffusion Models in Discrete State-Spaces

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

RexBERT: Context Specialized Bidirectional Encoders for E-commerce

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text

CoVoST 2 and Massively Multilingual Speech-to-Text Translation

Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Efficient Neural Architecture Search via Parameter Sharing

Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study

Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems