arXiv cs.CL Computation and Language
@cscl-bot.bsky.social
Unofficial bot by @vele.bsky.social w/ http://github.com/so-okada/bXiv https://arxiv.org/list/cs.CL/new
List https://bsky.app/profile/vele.bsky.social/lists/3lim7ccweqo2j
ModList https://bsky.app/profile/vele.bsky.social/lists/3lim3qnexsw2g
List https://bsky.app/profile/vele.bsky.social/lists/3lim7ccweqo2j
ModList https://bsky.app/profile/vele.bsky.social/lists/3lim3qnexsw2g
Reposted by arXiv cs.CL Computation and Language
Hu, Lin, Long, Ran, Jiang, Wang, Zhu, Xu, Wang, Pang: G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning https://arxiv.org/abs/2511.21688 https://arxiv.org/pdf/2511.21688 https://arxiv.org/html/2511.21688
November 27, 2025 at 6:32 AM
Hu, Lin, Long, Ran, Jiang, Wang, Zhu, Xu, Wang, Pang: G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning https://arxiv.org/abs/2511.21688 https://arxiv.org/pdf/2511.21688 https://arxiv.org/html/2511.21688
Reposted by arXiv cs.CL Computation and Language
Kay Liu, Yuwei Han, Haoyan Xu, Henry Peng Zou, Yue Zhao, Philip S. Yu: TAGFN: A Text-Attributed Graph Dataset for Fake News Detection in the Age of LLMs https://arxiv.org/abs/2511.21624 https://arxiv.org/pdf/2511.21624 https://arxiv.org/html/2511.21624
November 27, 2025 at 6:35 AM
Kay Liu, Yuwei Han, Haoyan Xu, Henry Peng Zou, Yue Zhao, Philip S. Yu: TAGFN: A Text-Attributed Graph Dataset for Fake News Detection in the Age of LLMs https://arxiv.org/abs/2511.21624 https://arxiv.org/pdf/2511.21624 https://arxiv.org/html/2511.21624
Reposted by arXiv cs.CL Computation and Language
Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas: Subjective Depth and Timescale Transformers: Learning Where and When to Compute https://arxiv.org/abs/2511.21408 https://arxiv.org/pdf/2511.21408 https://arxiv.org/html/2511.21408
November 27, 2025 at 6:34 AM
Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas: Subjective Depth and Timescale Transformers: Learning Where and When to Compute https://arxiv.org/abs/2511.21408 https://arxiv.org/pdf/2511.21408 https://arxiv.org/html/2511.21408
Reposted by arXiv cs.CL Computation and Language
Jiayuan Zhang, Kaiquan Chen, Zhihao Lu, Enshen Zhou, Qian Yu, Jing Zhang: Prune4Web: DOM Tree Pruning Programming for Web Agent https://arxiv.org/abs/2511.21398 https://arxiv.org/pdf/2511.21398 https://arxiv.org/html/2511.21398
November 27, 2025 at 6:29 AM
Jiayuan Zhang, Kaiquan Chen, Zhihao Lu, Enshen Zhou, Qian Yu, Jing Zhang: Prune4Web: DOM Tree Pruning Programming for Web Agent https://arxiv.org/abs/2511.21398 https://arxiv.org/pdf/2511.21398 https://arxiv.org/html/2511.21398
Reposted by arXiv cs.CL Computation and Language
Jiyun Bae, Hyunjong Ok, Sangwoo Mo, Jaeho Lee: Do Reasoning Vision-Language Models Inversely Scale in Test-Time Compute? A Distractor-centric Empirical Analysis https://arxiv.org/abs/2511.21397 https://arxiv.org/pdf/2511.21397 https://arxiv.org/html/2511.21397
November 27, 2025 at 6:32 AM
Jiyun Bae, Hyunjong Ok, Sangwoo Mo, Jaeho Lee: Do Reasoning Vision-Language Models Inversely Scale in Test-Time Compute? A Distractor-centric Empirical Analysis https://arxiv.org/abs/2511.21397 https://arxiv.org/pdf/2511.21397 https://arxiv.org/html/2511.21397
Reposted by arXiv cs.CL Computation and Language
Ariful Islam, Md Rifat Hossen, Abir Ahmed, B M Taslimul Haque: BanglaASTE: A Novel Framework for Aspect-Sentiment-Opinion Extraction in Bangla E-commerce Reviews Using Ensemble Deep Learning https://arxiv.org/abs/2511.21381 https://arxiv.org/pdf/2511.21381 https://arxiv.org/html/2511.21381
November 27, 2025 at 6:34 AM
Ariful Islam, Md Rifat Hossen, Abir Ahmed, B M Taslimul Haque: BanglaASTE: A Novel Framework for Aspect-Sentiment-Opinion Extraction in Bangla E-commerce Reviews Using Ensemble Deep Learning https://arxiv.org/abs/2511.21381 https://arxiv.org/pdf/2511.21381 https://arxiv.org/html/2511.21381
Reposted by arXiv cs.CL Computation and Language
Kirti Bhagat, Shaily Bhatt, Athul Velagapudi, Aditya Vashistha, Shachi Dave, Danish Pruthi: TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories https://arxiv.org/abs/2511.21322 https://arxiv.org/pdf/2511.21322 https://arxiv.org/html/2511.21322
November 27, 2025 at 6:32 AM
Kirti Bhagat, Shaily Bhatt, Athul Velagapudi, Aditya Vashistha, Shachi Dave, Danish Pruthi: TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories https://arxiv.org/abs/2511.21322 https://arxiv.org/pdf/2511.21322 https://arxiv.org/html/2511.21322
Reposted by arXiv cs.CL Computation and Language
Zheng Li, Yibing Song, Xin Zhang, Lei Luo, Xiang Li, Jian Yang: AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning https://arxiv.org/abs/2511.21188 https://arxiv.org/pdf/2511.21188 https://arxiv.org/html/2511.21188
November 27, 2025 at 6:31 AM
Zheng Li, Yibing Song, Xin Zhang, Lei Luo, Xiang Li, Jian Yang: AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning https://arxiv.org/abs/2511.21188 https://arxiv.org/pdf/2511.21188 https://arxiv.org/html/2511.21188
Reposted by arXiv cs.CL Computation and Language
Chungpa Lee, Thomas Zeng, Jongwon Jeong, Jy-yong Sohn, Kangwook Lee: How to Correctly Report LLM-as-a-Judge Evaluations https://arxiv.org/abs/2511.21140 https://arxiv.org/pdf/2511.21140 https://arxiv.org/html/2511.21140
November 27, 2025 at 6:33 AM
Chungpa Lee, Thomas Zeng, Jongwon Jeong, Jy-yong Sohn, Kangwook Lee: How to Correctly Report LLM-as-a-Judge Evaluations https://arxiv.org/abs/2511.21140 https://arxiv.org/pdf/2511.21140 https://arxiv.org/html/2511.21140
Reposted by arXiv cs.CL Computation and Language
Vladimir Berman: Zipf Distributions from Two-Stage Symbolic Processes: Stability Under Stochastic Lexical Filtering https://arxiv.org/abs/2511.21060 https://arxiv.org/pdf/2511.21060 https://arxiv.org/html/2511.21060
November 27, 2025 at 6:53 AM
Vladimir Berman: Zipf Distributions from Two-Stage Symbolic Processes: Stability Under Stochastic Lexical Filtering https://arxiv.org/abs/2511.21060 https://arxiv.org/pdf/2511.21060 https://arxiv.org/html/2511.21060
Reposted by arXiv cs.CL Computation and Language
Quan Xiao, Tianyi Chen: A Unified Understanding of Offline Data Selection and Online Self-refining Generation for Post-training LLMs https://arxiv.org/abs/2511.21056 https://arxiv.org/pdf/2511.21056 https://arxiv.org/html/2511.21056
November 27, 2025 at 6:33 AM
Quan Xiao, Tianyi Chen: A Unified Understanding of Offline Data Selection and Online Self-refining Generation for Post-training LLMs https://arxiv.org/abs/2511.21056 https://arxiv.org/pdf/2511.21056 https://arxiv.org/html/2511.21056
Reposted by arXiv cs.CL Computation and Language
Liangzu Peng, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Wei Xia, Stefano Soatto: Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression https://arxiv.org/abs/2511.21016 https://arxiv.org/pdf/2511.21016 https://arxiv.org/html/2511.21016
November 27, 2025 at 6:33 AM
Liangzu Peng, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Wei Xia, Stefano Soatto: Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression https://arxiv.org/abs/2511.21016 https://arxiv.org/pdf/2511.21016 https://arxiv.org/html/2511.21016
Reposted by arXiv cs.CL Computation and Language
Zheng, Sun, Dinh, Yanamandra, Jain, Liu, Hadap, Bhat, Aggarwal, Medioni, Harwath: RosettaSpeech: Zero-Shot Speech-to-Speech Translation from Monolingual Data https://arxiv.org/abs/2511.20974 https://arxiv.org/pdf/2511.20974 https://arxiv.org/html/2511.20974
November 27, 2025 at 6:35 AM
Zheng, Sun, Dinh, Yanamandra, Jain, Liu, Hadap, Bhat, Aggarwal, Medioni, Harwath: RosettaSpeech: Zero-Shot Speech-to-Speech Translation from Monolingual Data https://arxiv.org/abs/2511.20974 https://arxiv.org/pdf/2511.20974 https://arxiv.org/html/2511.20974
Reposted by arXiv cs.CL Computation and Language
Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass: Towards Audio Token Compression in Large Audio Language Models https://arxiv.org/abs/2511.20973 https://arxiv.org/pdf/2511.20973 https://arxiv.org/html/2511.20973
November 27, 2025 at 6:35 AM
Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass: Towards Audio Token Compression in Large Audio Language Models https://arxiv.org/abs/2511.20973 https://arxiv.org/pdf/2511.20973 https://arxiv.org/html/2511.20973
Reposted by arXiv cs.CL Computation and Language
Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar: TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs https://arxiv.org/abs/2511.20965 https://arxiv.org/pdf/2511.20965 https://arxiv.org/html/2511.20965
November 27, 2025 at 6:31 AM
Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar: TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs https://arxiv.org/abs/2511.20965 https://arxiv.org/pdf/2511.20965 https://arxiv.org/html/2511.20965
Reposted by arXiv cs.CL Computation and Language
Wang, Huang, Zhou, Yin, Bao, Lyu, Liu, Zhang, Wu, Fei-Fei, Li: ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction https://arxiv.org/abs/2511.20937 https://arxiv.org/pdf/2511.20937 https://arxiv.org/html/2511.20937
November 27, 2025 at 6:29 AM
Wang, Huang, Zhou, Yin, Bao, Lyu, Liu, Zhang, Wu, Fei-Fei, Li: ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction https://arxiv.org/abs/2511.20937 https://arxiv.org/pdf/2511.20937 https://arxiv.org/html/2511.20937
Reposted by arXiv cs.CL Computation and Language
Sree Bhattacharyya, Yaman Kumar Singla, Sudhir Yarram, Somesh Kumar Singh, Harini S I, James Z. Wang: Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries https://arxiv.org/abs/2511.20854 https://arxiv.org/pdf/2511.20854 https://arxiv.org/html/2511.20854
November 27, 2025 at 6:30 AM
Sree Bhattacharyya, Yaman Kumar Singla, Sudhir Yarram, Somesh Kumar Singh, Harini S I, James Z. Wang: Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries https://arxiv.org/abs/2511.20854 https://arxiv.org/pdf/2511.20854 https://arxiv.org/html/2511.20854
Reposted by arXiv cs.CL Computation and Language
Samuele Dell'Erba, Andrew D. Bagdanov: Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion https://arxiv.org/abs/2511.20821 https://arxiv.org/pdf/2511.20821 https://arxiv.org/html/2511.20821
November 27, 2025 at 6:30 AM
Samuele Dell'Erba, Andrew D. Bagdanov: Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion https://arxiv.org/abs/2511.20821 https://arxiv.org/pdf/2511.20821 https://arxiv.org/html/2511.20821
Reposted by arXiv cs.CL Computation and Language
Daeheon Jeong, Seoyeon Byun, Kihoon Son, Dae Hyun Kim, Juho Kim: CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design https://arxiv.org/abs/2511.20737 https://arxiv.org/pdf/2511.20737 https://arxiv.org/html/2511.20737
November 27, 2025 at 6:30 AM
Daeheon Jeong, Seoyeon Byun, Kihoon Son, Dae Hyun Kim, Juho Kim: CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design https://arxiv.org/abs/2511.20737 https://arxiv.org/pdf/2511.20737 https://arxiv.org/html/2511.20737
Reposted by arXiv cs.CL Computation and Language
Wang, Xie, Wang, Xiao, Chen, Sargeant, Steffek, Shao, Liu, Sun: Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts https://arxiv.org/abs/2511.20736 https://arxiv.org/pdf/2511.20736 https://arxiv.org/html/2511.20736
November 27, 2025 at 6:30 AM
Wang, Xie, Wang, Xiao, Chen, Sargeant, Steffek, Shao, Liu, Sun: Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts https://arxiv.org/abs/2511.20736 https://arxiv.org/pdf/2511.20736 https://arxiv.org/html/2511.20736
Reposted by arXiv cs.CL Computation and Language
Ali Madad (GiveCare): InvisibleBench: A Deployment Gate for Caregiving Relationship AI https://arxiv.org/abs/2511.20733 https://arxiv.org/pdf/2511.20733 https://arxiv.org/html/2511.20733
November 27, 2025 at 6:30 AM
Ali Madad (GiveCare): InvisibleBench: A Deployment Gate for Caregiving Relationship AI https://arxiv.org/abs/2511.20733 https://arxiv.org/pdf/2511.20733 https://arxiv.org/html/2511.20733
Reposted by arXiv cs.CL Computation and Language
Li, Elmahdy, Boyd, Wang, Garcia, Bhatia, Kass-Hout, Xiao, Hong: ST-PPO: Stabilized Off-Policy Proximal Policy Optimization for Multi-Turn Agents Training https://arxiv.org/abs/2511.20718 https://arxiv.org/pdf/2511.20718 https://arxiv.org/html/2511.20718
November 27, 2025 at 6:33 AM
Li, Elmahdy, Boyd, Wang, Garcia, Bhatia, Kass-Hout, Xiao, Hong: ST-PPO: Stabilized Off-Policy Proximal Policy Optimization for Multi-Turn Agents Training https://arxiv.org/abs/2511.20718 https://arxiv.org/pdf/2511.20718 https://arxiv.org/html/2511.20718
Yeganeh Kordi, Nihal V. Nayak, Max Zuo, Ilana Nguyen, Stephen H. Bach: Revisiting Generalization Across Difficulty Levels: It's Not So Easy https://arxiv.org/abs/2511.21692 https://arxiv.org/pdf/2511.21692 https://arxiv.org/html/2511.21692
November 27, 2025 at 6:30 AM
Yeganeh Kordi, Nihal V. Nayak, Max Zuo, Ilana Nguyen, Stephen H. Bach: Revisiting Generalization Across Difficulty Levels: It's Not So Easy https://arxiv.org/abs/2511.21692 https://arxiv.org/pdf/2511.21692 https://arxiv.org/html/2511.21692
Su, Diao, Lu, Liu, Xu, Dong, Fu, Belcak, Ye, Yin, Dong, Bakhturina, Yu, Choi, Kautz, Molchanov: ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration https://arxiv.org/abs/2511.21689 https://arxiv.org/pdf/2511.21689 https://arxiv.org/html/2511.21689
November 27, 2025 at 6:30 AM
Su, Diao, Lu, Liu, Xu, Dong, Fu, Belcak, Ye, Yin, Dong, Bakhturina, Yu, Choi, Kautz, Molchanov: ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration https://arxiv.org/abs/2511.21689 https://arxiv.org/pdf/2511.21689 https://arxiv.org/html/2511.21689
Wang, Li, Ni, Yeh, Emad, Lei, Robbins, Padthe, Xu, Li, Celikyilmaz, Raghavendra, Huang, Wu, Li: Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework https://arxiv.org/abs/2511.21686 https://arxiv.org/pdf/2511.21686 https://arxiv.org/html/2511.21686
November 27, 2025 at 6:30 AM
Wang, Li, Ni, Yeh, Emad, Lei, Robbins, Padthe, Xu, Li, Celikyilmaz, Raghavendra, Huang, Wu, Li: Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework https://arxiv.org/abs/2511.21686 https://arxiv.org/pdf/2511.21686 https://arxiv.org/html/2511.21686