Machine Learning

Sparser, Faster, Lighter Transformer Language Models

Sparser, Faster, Lighter Transformer Language ...

Machine Learning
Avatar
Edoardo Cetin
4 views
Off-Policy Value-Based Reinforcement Learning for Large Language Models

Off-Policy Value-Based Reinforcement Learning ...

Machine Learning
Avatar
librarian
4 views
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions

Byzantine-Robust and Differentially Private Fe...

Machine Learning
Avatar
librarian
4 views
TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

TreeTeaming: Autonomous Red-Teaming of Vision-...

Machine Learning
Avatar
Chunxiao Li
3 views
Can Graph Foundation Models Generalize Over Architecture?

Can Graph Foundation Models Generalize Over Ar...

Machine Learning
Avatar
librarian
2 views
Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?

Revisiting Quantum Code Generation: Where Shou...

Machine Learning
Avatar
librarian
4 views
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

On the Direction of RLVR Updates for LLM Reaso...

Machine Learning
Avatar
librarian
6 views
Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting

Noise Titration: Exact Distributional Benchmar...

Machine Learning
Avatar
librarian
6 views
Calibeating Made Simple

Calibeating Made Simple

Machine Learning
Avatar
librarian
6 views
Causal Evidence that Language Models use Confidence to Drive Behavior

Causal Evidence that Language Models use Confi...

Machine Learning
Avatar
librarian
7 views
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

Confidence-Based Decoding is Provably Efficien...

Machine Learning
Avatar
Changxiao Cai
9 views
Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration

Decoupling Exploration and Policy Optimization...

Machine Learning
Avatar
librarian
8 views
Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels

Scaling DoRA: High-Rank Adaptation via Factore...

Machine Learning
Avatar
librarian
10 views
Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization

Thinking Deeper, Not Longer: Depth-Recurrent T...

Machine Learning
Avatar
Hung-Hsuan Chen
4 views
Robustness, Cost, and Attack-Surface Concentration in Phishing Detection

Robustness, Cost, and Attack-Surface Concentra...

Machine Learning
Avatar
librarian
18 views
Online Learning and Equilibrium Computation with Ranking Feedback

Online Learning and Equilibrium Computation wi...

Machine Learning
Avatar
librarian
18 views
Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification

Position: Spectral GNNs Are Neither Spectral N...

Machine Learning
Avatar
Wei Pang
17 views
Hierarchical Latent Structure Learning through Online Inference

Hierarchical Latent Structure Learning through...

Machine Learning
Avatar
librarian
15 views
DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge

DyMoE: Dynamic Expert Orchestration with Mixed...

Machine Learning
Avatar
librarian
14 views
Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees

Rigorous Error Certification for Neural PDE So...

Machine Learning
Avatar
librarian
13 views
Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

Improving RCT-Based Treatment Effect Estimatio...

Machine Learning
Avatar
librarian
17 views
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

SOL-ExecBench: Speed-of-Light Benchmarking for...

Machine Learning
Avatar
librarian
15 views
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data

MIDST Challenge at SaTML 2025: Membership Infe...

Machine Learning
Avatar
Masoumeh Shafieinejad
12 views
CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks

CausalRM: Causal-Theoretic Reward Modeling for...

Machine Learning
Avatar
librarian
13 views
DriftGuard: Mitigating Asynchronous Data Drift in Federated Learning

DriftGuard: Mitigating Asynchronous Data Drift...

Machine Learning
Avatar
Yizhou Han
12 views
Only relative ranks matter in weight-clustered large language models

Only relative ranks matter in weight-clustered...

Machine Learning
Avatar
librarian
14 views
Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training

Beyond Muon: MUD (MomentUm Decorrelation) for ...

Machine Learning
Avatar
librarian
41 views
Unified Policy Value Decomposition for Rapid Adaptation

Unified Policy Value Decomposition for Rapid A...

Machine Learning
Avatar
librarian
12 views
Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems

Towards Infinitely Long Neural Simulations: Se...

Machine Learning
Avatar
librarian
12 views
Procedural Generation of Algorithm Discovery Tasks in Machine Learning

Procedural Generation of Algorithm Discovery T...

Machine Learning
Avatar
librarian
12 views
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention

CARE: Covariance-Aware and Rank-Enhanced Decom...

Machine Learning
Avatar
librarian
13 views
Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models

Cohomological Obstructions to Global Counterfa...

Machine Learning
Avatar
Rui Wu
11 views
Load more