| 201 |
RePair: Turning Retrieval Failures into Counterfactual Hard Pairs
Siyi Liu, Xiaorong Zhu, ... (+7 more)
|
|
cs.IR
|
0 |
21 days ago |
| 202 |
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
Minkyu Kim, Juhwan Choi, YoungBin Kim
|
|
cs.AI
|
0 |
21 days ago |
| 203 |
Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation
Yilun Liu, Boyu Luo, ... (+3 more)
|
|
cs.AI
|
0 |
21 days ago |
| 204 |
PhysWave: Physics-Guided Latent Diffusion Models for Controllable Spatial Audio Generation
Lingfeng Yao, Chenpei Huang, ... (+6 more)
|
|
cs.SD
|
0 |
21 days ago |
| 205 |
Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift
Yujia Liu, Jiayan Lin, ... (+7 more)
|
|
cs.CL
|
0 |
21 days ago |
| 206 |
CoCoA: Context-Conditional Cultural Alignment for Large Language Models
Kyungdon Lee, Wei Xu, ... (+3 more)
|
|
cs.CL
|
0 |
21 days ago |
| 207 |
GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation
Arka Mukherjee, Soham Roy, ... (+2 more)
|
|
cs.CV
|
0 |
21 days ago |
| 208 |
SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training
Zihan Wang, Anita Marie Slominska, ... (+11 more)
|
|
cs.CL
|
0 |
21 days ago |
| 209 |
Co-Evolutionary Prompt Optimization with Cross-Category Transfer for Zero-Shot Anomaly Detection
Sisi Zhu, Changwei Yu, ... (+2 more)
|
|
cs.CV
|
0 |
22 days ago |
| 210 |
When to Adapt: Conditional Memory Adapters for Retention-Preserving Domain Specialization
Jiayu Hou, Lei Wang
|
|
cs.CL
|
0 |
22 days ago |
| 211 |
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Daegyu Sung, Yukyeong Lee, ... (+3 more)
|
|
cs.SE
|
0 |
22 days ago |
| 212 |
Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning
Tatul Danielyan, Mariam Avetisyan, Hrant Davtyan
|
|
cs.CL
|
0 |
22 days ago |
| 213 |
Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning
Zhaolu Kang, Meixin Wu, ... (+7 more)
|
|
cs.CL
|
0 |
22 days ago |
| 214 |
SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization
Hojae Han, Jongyoon Kim, ... (+8 more)
|
|
cs.CL
|
0 |
22 days ago |
| 215 |
Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs
Abdelrahman Abdallah, Mohammed Ali, ... (+3 more)
|
|
cs.CL
|
0 |
22 days ago |
| 216 |
When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions
Zachary Ellis, Spencer Hazel, ... (+4 more)
|
|
cs.CL
|
0 |
22 days ago |
| 217 |
Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages
Kuan-Tang Huang, Cheng-Yeh Yang, ... (+4 more)
|
|
cs.CL
|
0 |
22 days ago |
| 218 |
Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation
Leandra Fichtel, Janek Prange, Henning Wachsmuth
|
|
cs.CL
|
0 |
22 days ago |
| 219 |
Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation
Ibrahim Mohamed Serouis, David Jaramillo Duque
|
|
cs.AI
|
0 |
22 days ago |
| 220 |
Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities
Millicent Ochieng, Felermino D. M. A. Ali, ... (+9 more)
|
|
cs.CL
|
0 |
22 days ago |
| 221 |
How Identity and Opinion Shape Political Sycophancy in LLMs
Li-Ni Fu, Chang-Chih Meng, ... (+3 more)
|
|
cs.AI
|
0 |
22 days ago |
| 222 |
HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide
Aman Prakash, Sourish Dasgupta, Tanmoy Chakraborty
|
|
cs.LG
|
0 |
22 days ago |
| 223 |
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Kejia Zhang, Tianyuan Zou, ... (+2 more)
|
|
cs.CR
|
0 |
22 days ago |
| 224 |
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Yucheng Du, Xiyang Hu
|
|
cs.CL
|
0 |
22 days ago |
| 225 |
A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges
Ruiyi Yan, Chenhui Chu, ... (+2 more)
|
|
cs.CR
|
0 |
22 days ago |
| 226 |
Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection
Yifan Xiang, Bin Liang, ... (+3 more)
|
|
cs.CL
|
0 |
22 days ago |
| 227 |
EmoLASP: Emotion Recognition with Language Models and Answer Set Programming
Thao Le, Michael Thielscher
|
|
cs.AI
|
0 |
22 days ago |
| 228 |
Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features
Keunhyeung Park, Seunguk Yu, YoungBin Kim
|
|
cs.CL
|
0 |
22 days ago |
| 229 |
AREAs-Lab: An Interactive Environment for AI-driven Requirement Elicitation for AI Systems
Pengshan Cai, Zihao Zhang, ... (+9 more)
|
|
cs.HC
|
0 |
22 days ago |
| 230 |
Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction
Zeyang Song, Tianchi Liu, ... (+4 more)
|
|
cs.SD
|
0 |
22 days ago |
| 231 |
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Tsung-Han Wu, Heekyung Lee, ... (+5 more)
|
|
cs.CL
|
0 |
22 days ago |
| 232 |
MERIT: Mitigating Exposure Bias in Generative XMC for User-Interest Propensity Modeling
Abhinav Mahajan, Arindam Sarkar, Prakash Mandayam Comar
|
|
cs.IR
|
0 |
23 days ago |
| 233 |
The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice
Jungseob Lee, Jaehyung Seo, Heuiseok Lim
|
|
cs.CL
|
0 |
23 days ago |
| 234 |
MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft
Sewoong Lee, Risham Sidhu, ... (+2 more)
|
|
cs.AI
|
0 |
23 days ago |
| 235 |
Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops
Faeze Ghorbanpour, Constanza Fierro, ... (+2 more)
|
|
cs.CL
|
0 |
23 days ago |
| 236 |
Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering
Shaozu Ding, Linan Song, Dajiang Suo
|
|
cs.CV
|
0 |
23 days ago |
| 237 |
PULSAR: Pooled Unified Late-Interaction Search and Retrieval for Enterprise Visual Document RAG
Benjamin Constable, Anup Roy, ... (+4 more)
|
|
cs.IR
|
0 |
23 days ago |
| 238 |
DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian
|
|
cs.LG
|
0 |
23 days ago |
| 239 |
Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation
V. S. D. S. Mahesh Akavarapu, Michael Daniel, Gerhard Jäger
|
|
cs.CL
|
0 |
23 days ago |
| 240 |
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
Di Wu, Sergey Troshin, ... (+3 more)
|
|
cs.CL
|
0 |
23 days ago |
| 241 |
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
Zhuoshi Pan, Qizhi Pei, ... (+5 more)
|
|
cs.CL
|
0 |
23 days ago |
| 242 |
Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Nan Li
|
|
cs.CL
|
0 |
23 days ago |
| 243 |
Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
Qing Ye, Meng-Hsuan Lin
|
|
cs.CL
|
0 |
23 days ago |
| 244 |
A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
Shihang Yang, Sanwoo Lee, ... (+2 more)
|
|
cs.CL
|
0 |
23 days ago |
| 245 |
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
Bryan Chen Zhengyu Tan, Weihua Zheng, ... (+31 more)
|
|
cs.CL
|
0 |
23 days ago |
| 246 |
CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
Jaewon Jung, Haizhong Zheng, ... (+4 more)
|
|
cs.CR
|
0 |
23 days ago |
| 247 |
AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning
Wonjun Lee, Jaehyuk Jang, ... (+3 more)
|
|
cs.CV
|
0 |
23 days ago |
| 248 |
Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration
Xiaoqing Wang, Keman Huang, ... (+4 more)
|
|
cs.AI
|
0 |
23 days ago |
| 249 |
REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features
Kai-Xuan Ding, Hao-Xiang Xu, ... (+4 more)
|
|
cs.AI
|
0 |
23 days ago |
| 250 |
Stay Within Your Bounds: Distance-Guided Decoding for Guaranteed Context-Free Grammar Compliance
Vincenzo Collura, Karim Tit, ... (+3 more)
|
|
cs.AI
|
0 |
23 days ago |