| 151 |
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
Seokil Ham, Jaehyuk Jang, ... (+2 more)
|
|
cs.AI
|
0 |
2 months ago |
| 152 |
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
Luoyu Chen, Weiqi Wang, ... (+6 more)
|
|
cs.CR
|
0 |
2 months ago |
| 153 |
AvAtar: Learning to Align via Active Optimal Transport
Qi Yu, Ruizhong Qiu, ... (+4 more)
|
|
cs.LG
|
0 |
2 months ago |
| 154 |
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Seojeong Park, Jiho Choi, ... (+4 more)
|
|
cs.CV
|
0 |
1 month ago |
| 155 |
Tracking the Behavioral Trajectories of Adapting Agents
Jonah Leshin, Manish Shah, Ian Timmis
|
|
cs.AI
|
0 |
1 month ago |
| 156 |
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
Wenhao Wang, Peizhi Niu, ... (+10 more)
|
|
cs.AI
|
0 |
1 month ago |
| 157 |
Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
Wei Deng, Xianlin Zhang, Mengshi Qi
|
|
cs.CV
|
0 |
1 month ago |
| 158 |
Speculative Sampling For Faster Molecular Dynamics
Arthur Kosmala, Stephan Günnemann, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 159 |
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
Xiang Li, Dianbo Liu, Kenji Kawaguchi
|
|
cs.CV
|
0 |
1 month ago |
| 160 |
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Yue Feng, Jingjing Li, ... (+10 more)
|
|
cs.CV
|
0 |
1 month ago |
| 161 |
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
Sahil Rahman, Maxx Richard Rahman
|
|
cs.AI
|
0 |
1 month ago |
| 162 |
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
Kyunghun Nam, Sumyeong Ahn
|
|
cs.LG
|
0 |
1 month ago |
| 163 |
ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
David Rundel, Fabian Fumagalli, ... (+3 more)
|
|
stat.ML
|
0 |
1 month ago |
| 164 |
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
Chengfeng Wu, Tao Zou, ... (+2 more)
|
|
cs.CV
|
0 |
1 month ago |
| 165 |
Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization
Yiming Wang, Baiqi Wu, ... (+4 more)
|
|
cs.CV
|
0 |
1 month ago |
| 166 |
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
Yikai Guo, Bin Wang, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 167 |
Rethinking Evaluation Paradigms in IBP-based Certified Training
Konstantin Kaulen, Hadar Shavit, Holger H. Hoos
|
|
cs.LG
|
0 |
1 month ago |
| 168 |
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
Jiangwei Chen, Xinyuan Niu, ... (+4 more)
|
|
cs.LG
|
0 |
1 month ago |
| 169 |
Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
Junhyoung Chung, Euijong Song, ... (+2 more)
|
|
stat.ML
|
0 |
1 month ago |
| 170 |
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
Ting Xu, Xu He, ... (+5 more)
|
|
cs.CL
|
0 |
1 month ago |
| 171 |
Private and Stable Test-Time Adaptation with Differential Privacy
Zefeng Li, Qiaoyue Tang, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 172 |
Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
Xiaolu Kang, Zhongyuan Wang, ... (+6 more)
|
|
cs.CV
|
0 |
1 month ago |
| 173 |
The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
Bing-Cheng Chuang, I-Hsuan Chu, ... (+4 more)
|
|
cs.RO
|
0 |
1 month ago |
| 174 |
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
Dimitris Oikonomou, Nicolas Loizou
|
|
math.OC
|
0 |
1 month ago |
| 175 |
Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
Taehan Kim, Sarrah Rose Mikhail Leung, ... (+2 more)
|
|
q-bio.BM
|
0 |
1 month ago |
| 176 |
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
Matthew Khoriaty, David Williams-King, Shi Feng
|
|
cs.CL
|
0 |
1 month ago |
| 177 |
An Algebraic View of the Expressivity of Recurrent Language Models
Franz Nowak, Ryan Cotterell, Reda Boumasmoud
|
|
cs.FL
|
0 |
1 month ago |
| 178 |
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
Minsik Choi, Geewook Kim
|
|
cs.LG
|
0 |
1 month ago |
| 179 |
Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
Hyeonwoo Cho, DongHyeon Baek, ... (+2 more)
|
|
cs.CV
|
0 |
1 month ago |
| 180 |
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Afsaneh Hasanebrahimi, Hanxun Huang, ... (+2 more)
|
|
cs.CV
|
0 |
1 month ago |
| 181 |
DOT-MoE: Differentiable Optimal Transport for MoEfication
Udbhav Bamba, Arnav Chavan, ... (+3 more)
|
|
cs.LG
|
0 |
1 month ago |
| 182 |
Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
Huayang Huang, Ruoyu Wang, ... (+6 more)
|
|
cs.CV
|
0 |
1 month ago |
| 183 |
PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
Weixing Chen, Zhuoqian Feng, ... (+7 more)
|
|
cs.CV
|
0 |
1 month ago |
| 184 |
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
Keyue Qiu, Xintong Wang, ... (+3 more)
|
|
q-bio.BM
|
0 |
1 month ago |
| 185 |
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
Yancheng Liu, Kenichi Maeda, Manan Pancholy
|
|
cs.CV
|
0 |
1 month ago |
| 186 |
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
Heng Zhao, Zilei Shao, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 187 |
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
Hongfei Du, Jiacheng Shi, ... (+3 more)
|
|
cs.CL
|
0 |
2 months ago |
| 188 |
Towards Optimal Robustness in Learning-Augmented Paging
Peng Chen, Hailiang Zhao, ... (+3 more)
|
|
cs.DS
|
0 |
2 months ago |
| 189 |
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
Rufeng Chen, Yue Chang, ... (+3 more)
|
|
cs.RO
|
0 |
2 months ago |
| 190 |
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
Wentao Mo, Yang Liu
|
|
cs.CV
|
0 |
2 months ago |
| 191 |
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
Boqian Wu, Qiao Xiao, ... (+7 more)
|
|
cs.LG
|
0 |
2 months ago |
| 192 |
Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
Hikmet Simsir, Ozgur S. Oguz
|
|
cs.LG
|
0 |
2 months ago |
| 193 |
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
Jun-Jie Yang, Chia-Heng Hsu, ... (+2 more)
|
|
cs.LG
|
0 |
2 months ago |
| 194 |
HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
Nasib Ullah, Jinbin Zhang, ... (+3 more)
|
|
cs.LG
|
0 |
2 months ago |
| 195 |
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, ... (+12 more)
|
|
cs.AI
|
0 |
2 months ago |
| 196 |
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
Bowen Tian, Caixue He, ... (+5 more)
|
|
cs.AI
|
0 |
2 months ago |
| 197 |
Position: Good Embodied Reward Models Need Bad Behavior Data
Ran Tian, Yilin Wu, Andrea Bajcsy
|
|
cs.RO
|
0 |
2 months ago |
| 198 |
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
Arda Uzunoglu, Alvin Zhang, Daniel Khashabi
|
|
cs.LG
|
0 |
2 months ago |
| 199 |
Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
Sanghoon Yu, Min-hwan Oh
|
|
stat.ML
|
0 |
2 months ago |
| 200 |
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
Wanlong Fang, Tianle Zhang, ... (+2 more)
|
|
cs.AI
|
0 |
2 months ago |