Machine Learning

A decoupled diffusion planner that adapts to changing cost limits by using cost-conditioned generation for safety and reward gradients for performance

A decoupled diffusion planner that adapts to c...

Machine Learning
Avatar
librarian
3 views
Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring

Trust, but Verify: Peeling Low-Bit Transformer...

Machine Learning
Avatar
Arian Eamaz
3 views
SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection

SpecKV: Adaptive Speculative Decoding with Com...

Machine Learning
Avatar
librarian
5 views
Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics

Beyond ECE: Calibrated Size Ratio, Risk Assess...

Machine Learning
Avatar
librarian
5 views
Stable GFlowNets with Probabilistic Guarantees

Stable GFlowNets with Probabilistic Guarantees

Machine Learning
Avatar
librarian
5 views
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time

Mitigating Multimodal LLMs Hallucinations via ...

Machine Learning
Avatar
Itai Allouche
5 views
Strait: Perceiving Priority and Interference in ML Inference Serving

Strait: Perceiving Priority and Interference i...

Machine Learning
Avatar
librarian
20 views
Global Optimality for Constrained Exploration via Penalty Regularization

Global Optimality for Constrained Exploration ...

Machine Learning
Avatar
librarian
21 views
Do Sparse Autoencoders Capture Concept Manifolds?

Do Sparse Autoencoders Capture Concept Manifolds?

Machine Learning
Avatar
librarian
50 views
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning

Latent-GRPO: Group Relative Policy Optimizatio...

Machine Learning
Avatar
librarian
16 views
An adaptive wavelet-based PINN for problems with localized high-magnitude source

An adaptive wavelet-based PINN for problems wi...

Machine Learning
Avatar
librarian
17 views
Exploration Hacking: Can LLMs Learn to Resist RL Training?

Exploration Hacking: Can LLMs Learn to Resist ...

Machine Learning
Avatar
librarian
17 views
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

Linear-Core Surrogates: Smooth Loss Functions ...

Machine Learning
Avatar
librarian
17 views
Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning

Kernelized Advantage Estimation: From Nonparam...

Machine Learning
Avatar
librarian
18 views
FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

FedHarmony: Harmonizing Heterogeneous Label Co...

Machine Learning
Avatar
Yuheng Jia
19 views
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework

Exploring the Potential of Probabilistic Trans...

Machine Learning
Avatar
librarian
27 views
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding

Accelerating RL Post-Training Rollouts via Sys...

Machine Learning
Avatar
librarian
24 views
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data

Language Diffusion Models are Associative Memo...

Machine Learning
Avatar
librarian
24 views
Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics

Uncertainty-Aware Predictive Safety Filters fo...

Machine Learning
Avatar
librarian
26 views
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Unifying Sparse Attention with Hierarchical Me...

Machine Learning
Avatar
Zihan Zhao
28 views
Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

Hyper Input Convex Neural Networks for Shape C...

Machine Learning
Avatar
librarian
25 views
Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics

Teacher Forcing as Generalized Bayes: Optimiza...

Machine Learning
Avatar
librarian
24 views
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning

TSN-Affinity: Similarity-Driven Parameter Reus...

Machine Learning
Avatar
librarian
27 views
Investigation into In-Context Learning Capabilities of Transformers

Investigation into In-Context Learning Capabil...

Machine Learning
Avatar
librarian
24 views
Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Conditional misalignment: common interventions...

Machine Learning
Avatar
librarian
23 views
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum

How Fast Should a Model Commit to Supervision?...

Machine Learning
Avatar
librarian
23 views
VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification

VAE-Inf: A statistically interpretable generat...

Machine Learning
Avatar
Hongfei Wu
24 views
Optimization-Free Topological Sort for Causal Discovery via the Schur Complement of Score Jacobians

Optimization-Free Topological Sort for Causal ...

Machine Learning
Avatar
librarian
23 views
QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention

QFlash: Bridging Quantization and Memory Effic...

Machine Learning
Avatar
librarian
23 views
On Halting vs Converging in Recurrent Graph Neural Networks

On Halting vs Converging in Recurrent Graph Ne...

Machine Learning
Avatar
librarian
20 views
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning

SpecRLBench: A Benchmark for Generalization in...

Machine Learning
Avatar
librarian
25 views
Scalable Hyperparameter-Divergent Ensemble Training with Automatic Learning Rate Exploration for Large Models

Scalable Hyperparameter-Divergent Ensemble Tra...

Machine Learning
Avatar
librarian
21 views
Load more