| 501 |
FlowFake: Liquid Networks for Audio Deepfake Detection
Shivaay Dhondiyal, Divyansh Sharma, Dinesh Kumar Vishwakarma
|
|
cs.SD
|
0 |
1 month ago |
| 502 |
Emergent Alignment
Martin Kolář
|
|
cs.AI
|
0 |
1 month ago |
| 503 |
LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data
Akshat Dasula, Prasanna Desikan, Jaideep Srivastava
|
|
cs.AI
|
0 |
1 month ago |
| 504 |
3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning
Ellina Zhang, Madhaven Iyengar, ... (+5 more)
|
|
cs.LG
|
0 |
1 month ago |
| 505 |
Native Active Perception as Reasoning for Omni-Modal Understanding
Zhenghao Xing, Ruiyang Xu, ... (+9 more)
|
|
cs.CV
|
0 |
1 month ago |
| 506 |
Detecting Hidden ML Training With Zero-Overhead Telemetry
Robi Rahman, Sabiha Tajdari
|
|
cs.LG
|
0 |
1 month ago |
| 507 |
Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-Experts
Tho Tran Huu, Huu-Tuan Nguyen, ... (+5 more)
|
|
cs.LG
|
0 |
1 month ago |
| 508 |
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
Zheng He, Danica J. Sutherland
|
|
stat.ML
|
0 |
1 month ago |
| 509 |
LARE: Low-Attention Region Encoding for Text-Image Retrieval
Abdulmalik Alquwayfili, Faisal Almeshal, ... (+9 more)
|
|
cs.CV
|
0 |
1 month ago |
| 510 |
Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
Ioannis Prokopiou, Pantelis Vikatos, ... (+3 more)
|
|
cs.SD
|
0 |
1 month ago |
| 511 |
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
Guannan Lai, Haoran Hu, Han-Jia Ye
|
|
cs.LG
|
0 |
1 month ago |
| 512 |
Private Learning with Public Feature Conditioning
Shuli Jiang, Walid Krichene, Nicolas Mayoraz
|
|
cs.LG
|
0 |
1 month ago |
| 513 |
TimeLAVA: Learning-Agnostic Data Valuation for Time Series
Wenqin Liu, Weizhi Quan, ... (+6 more)
|
|
stat.ML
|
0 |
1 month ago |
| 514 |
ForecastBench-Sim: A Simulated-World Forecasting Benchmark
Jaeho Lee, Nick Merrill, Ezra Karger
|
|
cs.AI
|
0 |
1 month ago |
| 515 |
Steerable Cultural Preference Optimization of Reward Models
Minsik Oh, Advit Deepak, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 516 |
Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops
Denis Savytski, Aiden Lei, ... (+5 more)
|
|
cs.CV
|
0 |
1 month ago |
| 517 |
SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR
Siddharth Aphale, Kelly Liu
|
|
cs.LG
|
0 |
1 month ago |
| 518 |
Task-Restricted Symmetries in Recurrent Weight Space
Simon Dräger
|
|
cs.LG
|
0 |
1 month ago |
| 519 |
Beyond Prediction: Tail-Aware Scheduling for LLM Inference
Yueying Li, Yuanfan Chen, ... (+7 more)
|
|
cs.LG
|
0 |
1 month ago |
| 520 |
Searching for Synergy in Shared Workspace Human-AI Collaboration
Nachiket Kotalwar, Rohini Das, Carolyn Rose
|
|
cs.AI
|
0 |
1 month ago |
| 521 |
Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
Yingshuo Wang, Xian Sun, ... (+5 more)
|
|
cs.LG
|
0 |
1 month ago |
| 522 |
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
Nils Morbitzer, Jonathan Evers, ... (+5 more)
|
|
cs.CV
|
0 |
1 month ago |
| 523 |
Adaptive Volumetric Mechanical Property Fields Invariant to Resolution
Rishit Dagli, Donglai Xiang, ... (+5 more)
|
|
cs.CV
|
0 |
1 month ago |
| 524 |
Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation
Ido Nitzan Hidekel, Dan Raviv
|
|
cs.LG
|
0 |
1 month ago |
| 525 |
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
Lalit Yadav, Akshaj Gurugubelli
|
|
cs.AI
|
0 |
1 month ago |
| 526 |
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
Mikołaj Zasada, Łukasz Struski, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 527 |
Dimensionality Controls When Modularity Helps in Continual Learning
Kathrin Korte, Christian Medeiros Adriano, ... (+3 more)
|
|
cs.LG
|
0 |
1 month ago |
| 528 |
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
Viet-Hoang Tran, Vinh Khanh Bui, ... (+3 more)
|
|
cs.LG
|
0 |
1 month ago |
| 529 |
Conservation Laws for Modern Neural Architectures
Viet-Hoang Tran, Vinh Khanh Bui, ... (+4 more)
|
|
cs.LG
|
0 |
1 month ago |
| 530 |
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
Jiahao Wang, Bingyu Liang, ... (+6 more)
|
|
cs.CL
|
0 |
1 month ago |
| 531 |
Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
Longhui Zhang, Jiahao Wang, ... (+4 more)
|
|
cs.CL
|
0 |
1 month ago |
| 532 |
Temporal Preference Optimization for Unsupervised Retrieval
HyunJin Kim, Jaejun Shim, ... (+2 more)
|
|
cs.IR
|
0 |
1 month ago |
| 533 |
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
Yuxiang Luo, Haonan Long, ... (+7 more)
|
|
cs.LG
|
0 |
1 month ago |
| 534 |
A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction
Yuxiang Luo, Chen Wang, Nan Tang
|
|
cs.LG
|
0 |
1 month ago |
| 535 |
Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning
Yanwei Cui, Xing Zhang, ... (+5 more)
|
|
cs.AI
|
0 |
1 month ago |
| 536 |
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
Yifu Ding, Jiacheng Wang, ... (+5 more)
|
|
cs.LG
|
0 |
1 month ago |
| 537 |
A Machine-Learned Comorbidity Index
Suleman Baloch, Kishlay Jha, ... (+3 more)
|
|
cs.AI
|
0 |
1 month ago |
| 538 |
The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
Huu Danh Nguyen
|
|
cs.LG
|
0 |
1 month ago |
| 539 |
NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama
Logan Mann, Abdur Rahman, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 540 |
Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3
Jay Jung, Xiaohan Zhang, ... (+9 more)
|
|
q-bio.QM
|
0 |
1 month ago |
| 541 |
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Subramanyam Sahoo, Aman Chadha, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 542 |
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Haoran Jin, Xiting Wang, ... (+3 more)
|
|
cs.LG
|
0 |
1 month ago |
| 543 |
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
Dvir Alsheich, Adar Peleg, ... (+4 more)
|
|
cs.AI
|
0 |
1 month ago |
| 544 |
Latent Actions from Factorized Transition Effects under Agent Ambiguity
Heejeong Nam, Chandradithya S Jonnalagadda, ... (+3 more)
|
|
cs.AI
|
0 |
1 month ago |
| 545 |
ITSPACE: Monotone Gaussian Optimal Transport Updates
Woojoo Na, Jennifer Dy
|
|
cs.LG
|
0 |
1 month ago |
| 546 |
MuonSSM: Orthogonalizing State Space Models for Sequence Modeling
Thai-Khanh Nguyen, Ngoc-Bich-Uyen Vo, ... (+3 more)
|
|
cs.LG
|
0 |
1 month ago |
| 547 |
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring
Max Fomin, Elad David, Amit LeVi
|
|
cs.LG
|
0 |
1 month ago |
| 548 |
REAR: Test-time Preference Realignment through Reward Decomposition
Fuxiang Zhang, Pengcheng Wang, ... (+7 more)
|
|
cs.CL
|
0 |
1 month ago |
| 549 |
BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
Haitao Wu, Qirui Zhang, ... (+9 more)
|
|
cs.CV
|
0 |
1 month ago |
| 550 |
Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization
Marcelina Marjankowska, Valerio Modugno, Paolo Barucca
|
|
cs.LG
|
0 |
1 month ago |