| 201 |
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
Wentao Mo, Yang Liu
|
|
cs.CV
|
0 |
19 days ago |
| 202 |
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
Boqian Wu, Qiao Xiao, ... (+7 more)
|
|
cs.LG
|
0 |
19 days ago |
| 203 |
Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
Hikmet Simsir, Ozgur S. Oguz
|
|
cs.LG
|
0 |
19 days ago |
| 204 |
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
Jun-Jie Yang, Chia-Heng Hsu, ... (+2 more)
|
|
cs.LG
|
0 |
19 days ago |
| 205 |
HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
Nasib Ullah, Jinbin Zhang, ... (+3 more)
|
|
cs.LG
|
0 |
19 days ago |
| 206 |
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, ... (+12 more)
|
|
cs.AI
|
0 |
19 days ago |
| 207 |
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
Bowen Tian, Caixue He, ... (+5 more)
|
|
cs.AI
|
0 |
19 days ago |
| 208 |
Position: Good Embodied Reward Models Need Bad Behavior Data
Ran Tian, Yilin Wu, Andrea Bajcsy
|
|
cs.RO
|
0 |
19 days ago |
| 209 |
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 |
19 days ago |
| 210 |
Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
Sanghoon Yu, Min-hwan Oh
|
|
stat.ML
|
0 |
19 days ago |
| 211 |
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
Wanlong Fang, Tianle Zhang, ... (+2 more)
|
|
cs.AI
|
0 |
19 days ago |
| 212 |
COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space
Yao Luan, Ni Mu, ... (+4 more)
|
|
cs.LG
|
0 |
19 days ago |
| 213 |
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
Shihao Wang, Xueru Zhang
|
|
cs.LG
|
0 |
19 days ago |
| 214 |
Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
Qiao Xiao, Boqian Wu, ... (+7 more)
|
|
cs.LG
|
0 |
20 days ago |
| 215 |
Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
Jan Philip Walter, Shashank Agnihotri, Margret Keuper
|
|
cs.CV
|
0 |
20 days ago |
| 216 |
Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated
Rashid Mushkani
|
|
cs.CV
|
0 |
20 days ago |
| 217 |
Latent Diffusion Pretraining for Crystal Property Prediction
Shrimon Mukherjee, Kishalay Das, ... (+3 more)
|
|
cs.LG
|
0 |
20 days ago |
| 218 |
RADE: Random Add-Drop Edge as a Regularizer
Danial Saber, Amirali Salehi-Abari
|
|
cs.LG
|
0 |
20 days ago |
| 219 |
SORA: Free Second-Order Attacks in Fast Adversarial Training
Mazdak Teymourian, Ramtin Moslemi, ... (+2 more)
|
|
cs.LG
|
0 |
20 days ago |
| 220 |
Preserving Plasticity in Continual Learning via Dynamical Isometry
Andries Rosseau, Robert Müller, Ann Nowé
|
|
cs.LG
|
0 |
11 days ago |
| 221 |
Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback
Rishabh Sabharwal, Hongru Wang, ... (+2 more)
|
|
cs.AI
|
0 |
11 days ago |
| 222 |
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, ... (+7 more)
|
|
cs.LG
|
0 |
11 days ago |
| 223 |
FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
Yuhan Ma, Yong Li, Stefan Schmid
|
|
cs.CR
|
0 |
11 days ago |
| 224 |
Temporal-Aware Reasoning Optimization for Video Temporal Grounding
Minghang Zheng, Zihao Yin, ... (+3 more)
|
|
cs.CV
|
0 |
11 days ago |
| 225 |
EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
Yuan Zeng, Yujia Shi, ... (+7 more)
|
|
cs.CV
|
0 |
11 days ago |
| 226 |
The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection
Hyunseok Paeng
|
|
cs.LG
|
0 |
11 days ago |
| 227 |
Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis
Hyeji Choi, Yongtaek Lim, Minwoo Kim
|
|
cs.CL
|
0 |
11 days ago |
| 228 |
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
Yongtaek Lim, Hyeji Choi, Minwoo Kim
|
|
cs.AI
|
0 |
11 days ago |
| 229 |
Improved Convergence Analysis of Topology Dependence in Decentralized SGD
Yuki Takezawa, Anastasia Koloskova, Sebastian U. Stich
|
|
cs.LG
|
0 |
11 days ago |
| 230 |
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
Zheng Liu, Chen Gong, ... (+7 more)
|
|
cs.CR
|
0 |
11 days ago |
| 231 |
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
Lena Krieger, Xuan Zhao, ... (+4 more)
|
|
cs.LG
|
0 |
11 days ago |
| 232 |
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
Jike Zhong, Yuxiang Lai, ... (+6 more)
|
|
cs.LG
|
0 |
11 days ago |
| 233 |
SafeRun: Enabling Determinism in LLM Planning for Running
Meilin Chen, Zepeng Zhai, ... (+2 more)
|
|
cs.CL
|
0 |
11 days ago |
| 234 |
Scaling by Diversified Experience for Vision-Language-Action Models
Leiyu Wang, Zhaofengnian Wang, ... (+4 more)
|
|
cs.CV
|
0 |
11 days ago |
| 235 |
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
Runsong Zhu, Jiaxin Guo, ... (+10 more)
|
|
cs.CV
|
0 |
11 days ago |
| 236 |
Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
Vladimir Braverman, Chen Wang, ... (+2 more)
|
|
cs.LG
|
0 |
11 days ago |
| 237 |
Rethinking 3D Shape Generation: Diffusion over Superquadrics
Zhiyang Liu, Wanze Li, ... (+5 more)
|
|
cs.CV
|
0 |
11 days ago |
| 238 |
Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models
Ting Wang, Yuanjie Shi, ... (+2 more)
|
|
cs.AI
|
0 |
12 days ago |
| 239 |
STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning
Sumin Park, Noseong Park
|
|
cs.AI
|
0 |
12 days ago |
| 240 |
Q-Delta: Beyond Key-Value Associative State Evolution
Sumin Park, Seojin Kim, Noseong Park
|
|
cs.AI
|
0 |
12 days ago |
| 241 |
Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
Blanka Köver, Alexandra Butoi, ... (+3 more)
|
|
cs.LG
|
0 |
12 days ago |
| 242 |
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
Xingyue Zhao, Wenke Huang, ... (+8 more)
|
|
cs.CV
|
0 |
12 days ago |
| 243 |
Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy
Yu Wei, Alexander Bienstock, Antigoni Polychroniadou
|
|
cs.CR
|
0 |
12 days ago |
| 244 |
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
Yishuo Cai, Xingyu Guo, ... (+9 more)
|
|
cs.CL
|
0 |
12 days ago |
| 245 |
Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition
Daniel Chen, Qicong Hu, ... (+3 more)
|
|
cs.LG
|
0 |
12 days ago |
| 246 |
Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models
Subramanyam Sahoo
|
|
cs.CL
|
0 |
12 days ago |
| 247 |
What Makes a Desired Graph for Relational Deep Learning?
Yao Cheng, Siqiang Luo
|
|
cs.AI
|
0 |
12 days ago |
| 248 |
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry
Xunye Tian, Zhijian Zhou, ... (+2 more)
|
|
stat.ML
|
0 |
12 days ago |
| 249 |
Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics
Antonio Franca, Alexander Tong
|
|
cs.CL
|
0 |
12 days ago |
| 250 |
Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection
Mudit Sinha, Sanika Chavan
|
|
cs.CR
|
0 |
12 days ago |