| 451 |
Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models
Haobo Xu, Sirui Chen, ... (+6 more)
|
|
cs.CL
|
0 |
22 days ago |
| 452 |
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
Huaiyuan Yao, Xiaoou Liu, ... (+3 more)
|
|
cs.AI
|
0 |
22 days ago |
| 453 |
Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems
Yiran Zhao, Lu Zhou, ... (+5 more)
|
|
cs.AI
|
0 |
22 days ago |
| 454 |
Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage
Weifeng Jiang, Ruirui Chen, ... (+4 more)
|
|
cs.CL
|
0 |
22 days ago |
| 455 |
IDEEA: training-free Input-Dependent stEEring via Activation cluster matching
Zheng Wang, Muchen Li, ... (+2 more)
|
|
cs.CL
|
0 |
22 days ago |
| 456 |
Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models
Tianqi Xiao, Shiyao Cui, ... (+3 more)
|
|
cs.MM
|
0 |
22 days ago |
| 457 |
MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity
Yiran Zhang, Jinwen Liu, ... (+8 more)
|
|
cs.AI
|
0 |
22 days ago |
| 458 |
Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents
Yanting Yang, Can Jin, ... (+7 more)
|
|
cs.LG
|
0 |
22 days ago |
| 459 |
NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis
Wuche Liu, Yiran Qiao, ... (+5 more)
|
|
cs.CL
|
0 |
22 days ago |
| 460 |
On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers
Vignesh Prabhakar, Jialing Pan, Anil Babu Ankisettipalli
|
|
cs.LG
|
0 |
23 days ago |
| 461 |
CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing
Huu Huy Nguyen, Chien Van Nguyen, ... (+5 more)
|
|
cs.LG
|
0 |
23 days ago |
| 462 |
Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets
Kunal Jadhav, Siddhesh More
|
|
cs.CL
|
0 |
23 days ago |
| 463 |
Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis
Yagna Manasa Boyapati, Chong Yu, ... (+2 more)
|
|
cs.CR
|
0 |
23 days ago |
| 464 |
Thinking effort aligns between humans and reasoning models in abductive reasoning
Henry Arthur
|
|
cs.CL
|
0 |
23 days ago |
| 465 |
ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
Aaryan Kapoor, Md Abdullah Al Hafiz Khan
|
|
cs.SE
|
0 |
23 days ago |
| 466 |
Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
S M Masrur Ahmed, Jaspal Subhlok
|
|
cs.CL
|
0 |
23 days ago |
| 467 |
Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
Chen Chen, Mohsen Nayebi Kerdabadi, ... (+3 more)
|
|
cs.LG
|
0 |
23 days ago |
| 468 |
How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?
Wei Hu, Xiaolong Tu, ... (+4 more)
|
|
cs.CL
|
0 |
23 days ago |
| 469 |
Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization
Yixuan Wang, Freda Shi, Kanishka Misra
|
|
cs.CL
|
0 |
23 days ago |
| 470 |
VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages
Usneek Singh, Poorvaja Veera Balaji Kumar, ... (+5 more)
|
|
cs.CL
|
0 |
23 days ago |
| 471 |
MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models
Tawsif Tashwar Dipto, Mehedi Ahamed, ... (+6 more)
|
|
cs.CL
|
0 |
23 days ago |
| 472 |
Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation
Himil Vasava, Ming Jiang
|
|
cs.CL
|
0 |
23 days ago |
| 473 |
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
Jingtan Wang, Arun Verma, ... (+5 more)
|
|
cs.CL
|
0 |
23 days ago |
| 474 |
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Giovanni Bonetta, Matteo Merler, ... (+3 more)
|
|
cs.AI
|
0 |
23 days ago |
| 475 |
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
Manish Gupta, Chaitanya Giri, Jayasimha Talur
|
|
cs.CL
|
0 |
23 days ago |
| 476 |
SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue
Stephanie Fong, Yiwen Jiang, ... (+13 more)
|
|
cs.CL
|
0 |
23 days ago |
| 477 |
TempCloze: Can Video-LLMs Identify the Missing Middle?
Wenqi Pei, Henry Hengyuan Zhao, ... (+5 more)
|
|
cs.CV
|
0 |
23 days ago |
| 478 |
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Yitong Guo, Xiaoyi Chen, ... (+3 more)
|
|
cs.CR
|
0 |
23 days ago |
| 479 |
Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation
Yixuan Liu, Lin Chen, ... (+3 more)
|
|
cs.DL
|
0 |
23 days ago |
| 480 |
From Rollouts to Recipes: Self-Contained Post-Training for LLMs
Yifei Li, Lingling Zhang, ... (+4 more)
|
|
cs.CL
|
0 |
23 days ago |
| 481 |
When Tokenization is Secretly Output Supervision
Tanja Baeumel, Josef van Genabith, Simon Ostermann
|
|
cs.CL
|
0 |
23 days ago |
| 482 |
IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals
Md. Atabuzzaman, Christian Alexander, Chris Thomas
|
|
cs.CV
|
0 |
23 days ago |
| 483 |
Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA
Nishant Mishra, Ameen Abu-Hanna, Iacer Calixto
|
|
cs.CL
|
0 |
23 days ago |
| 484 |
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
Jun Hou, Priya Pitre, ... (+2 more)
|
|
cs.AI
|
0 |
23 days ago |
| 485 |
Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
Mikhail Sonkin, Tanja Baeumel, ... (+3 more)
|
|
cs.CL
|
0 |
23 days ago |
| 486 |
CHARM: Character Hallucination for Multicultural Role Play Benchmark
Sunkyung Han, Nahyeon Park, ... (+3 more)
|
|
cs.CL
|
0 |
23 days ago |
| 487 |
Probing Factual Knowledge Transfer with Training Data Interventions
Romina Oji, Marc Braun, ... (+3 more)
|
|
cs.CL
|
0 |
23 days ago |
| 488 |
LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting
Yufei Chen, Yiran Zhao, ... (+4 more)
|
|
cs.AI
|
0 |
23 days ago |
| 489 |
VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models
Zhiqi Huang, Vivek Datla, ... (+4 more)
|
|
cs.CL
|
0 |
23 days ago |
| 490 |
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
Mian Zhong, Katherine A. Keith, Anjalie Field
|
|
cs.CL
|
0 |
23 days ago |
| 491 |
Reliability Challenges in Diffusion Vision-Language Models
Md. Atabuzzaman, Chris Thomas
|
|
cs.CV
|
0 |
23 days ago |
| 492 |
MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval
Debanjan Mahata, Atharva Tendle, ... (+3 more)
|
|
cs.IR
|
0 |
23 days ago |
| 493 |
Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models
Tian Fang, Gaël Guibon, Davide Buscaldi
|
|
cs.CL
|
0 |
23 days ago |
| 494 |
From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
Wenhe Sun, Cunxiang Wang, ... (+2 more)
|
|
cs.CL
|
0 |
23 days ago |
| 495 |
Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation
Thibaut Thonet, Jos Rozen, Laurent Besacier
|
|
cs.CL
|
0 |
23 days ago |
| 496 |
Prompt-Robust Language Models: Which Training Strategies Work?
Frederic Sadrieh, Michal Štefánik
|
|
cs.AI
|
0 |
23 days ago |
| 497 |
Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
Phong Trinh Duy, Trang Dang Yen, ... (+6 more)
|
|
cs.SE
|
0 |
23 days ago |
| 498 |
On the Design Fundamentals of Pixel Text Representation Learning
Chaohao Yuan, Ruifeng Yuan, ... (+5 more)
|
|
cs.CV
|
0 |
23 days ago |
| 499 |
Does task decomposition improve automatic NLG evaluation?
Sebastian Steindl, Nikos Voskarides, ... (+2 more)
|
|
cs.CL
|
0 |
23 days ago |
| 500 |
Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
Riza Setiawan Soetedjo, Yusuke Sakai, ... (+3 more)
|
|
cs.CL
|
0 |
23 days ago |