Machine Learning

Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference

Relative Entropy Estimation in Function Space:...

Machine Learning
Avatar
Chao Wang
1 view
Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples

Closing the Domain Gap in Biomedical Imaging b...

Machine Learning
Avatar
Günter Klambauer
2 views
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

ParetoSlider: Diffusion Models Post-Training f...

Machine Learning
Avatar
librarian
2 views
Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling

Stream-CQSA: Avoiding Out-of-Memory in Attenti...

Machine Learning
Avatar
librarian
2 views
Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

Occupancy Reward Shaping: Improving Credit Ass...

Machine Learning
Avatar
librarian
2 views
Amortized Vine Copulas for High-Dimensional Density and Information Estimation

Amortized Vine Copulas for High-Dimensional De...

Machine Learning
Avatar
librarian
2 views
Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales

Variance Is Not Importance: Structural Analysi...

Machine Learning
Avatar
Samuel Salfati
2 views
MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

MGDA-Decoupled: Geometry-Aware Multi-Objective...

Machine Learning
Avatar
librarian
2 views
FASTER: Value-Guided Sampling for Fast RL

FASTER: Value-Guided Sampling for Fast RL

Machine Learning
Avatar
Perry Dong
10 views
Safe Continual Reinforcement Learning in Non-stationary Environments

Safe Continual Reinforcement Learning in Non-s...

Machine Learning
Avatar
Austin Coursey
12 views
Generalization at the Edge of Stability

Generalization at the Edge of Stability

Machine Learning
Avatar
librarian
29 views
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation

Unsupervised Confidence Calibration for Reason...

Machine Learning
Avatar
Thomas Zollo
12 views
TEMPO: Scaling Test-time Training for Large Reasoning Models

TEMPO: Scaling Test-time Training for Large Re...

Machine Learning
Avatar
librarian
14 views
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit

LLMs Know They're Wrong and Agree Anyway: The ...

Machine Learning
Avatar
librarian
7 views
Evaluation-driven Scaling for Scientific Discovery

Evaluation-driven Scaling for Scientific Discovery

Machine Learning
Avatar
librarian
8 views
EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

EVPO: Explained Variance Policy Optimization f...

Machine Learning
Avatar
librarian
8 views
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

Train Separately, Merge Together: Modular Post...

Machine Learning
Avatar
librarian
15 views
Bounded Ratio Reinforcement Learning

Bounded Ratio Reinforcement Learning

Machine Learning
Avatar
librarian
14 views
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

Efficient Diffusion Models under Nonconvex Equ...

Machine Learning
Avatar
librarian
13 views
M100: An Orchestrated Dataflow Architecture Powering General AI Computing

M100: An Orchestrated Dataflow Architecture Po...

Machine Learning
Avatar
Yan Xie
18 views
Neural Garbage Collection: Learning to Forget while Learning to Reason

Neural Garbage Collection: Learning to Forget ...

Machine Learning
Avatar
librarian
14 views
Towards a Foundation-Model Paradigm for Aerodynamic Prediction in Three-dimensional Design

Towards a Foundation-Model Paradigm for Aerody...

Machine Learning
Avatar
librarian
14 views
Guardrails in Logit Space: Safety Token Regularization for LLM Alignment

Guardrails in Logit Space: Safety Token Regula...

Machine Learning
Avatar
librarian
5 views
Continual Safety Alignment via Gradient-Based Sample Selection

Continual Safety Alignment via Gradient-Based ...

Machine Learning
Avatar
Thong Bach
6 views
Demystifying the unreasonable effectiveness of online alignment methods

Demystifying the unreasonable effectiveness of...

Machine Learning
Avatar
Enoch Hyunwook Kang
6 views
LASER: Low-Rank Activation SVD for Efficient Recursion

LASER: Low-Rank Activation SVD for Efficient R...

Machine Learning
Avatar
librarian
6 views
Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study

Revisiting Auxiliary Losses for Conditional De...

Machine Learning
Avatar
librarian
6 views
RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning

RL-STPA: Adapting System-Theoretic Hazard Anal...

Machine Learning
Avatar
Steven Senczyszyn
26 views
How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

How Embeddings Shape Graph Neural Networks: Cl...

Machine Learning
Avatar
Nouhaila Innan
22 views
Benchmarking Optimizers for MLPs in Tabular Deep Learning

Benchmarking Optimizers for MLPs in Tabular De...

Machine Learning
Avatar
Yury Gorishniy
24 views
Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks

Beyond the Laplacian: Doubly Stochastic Matric...

Machine Learning
Avatar
Zhaobo Hu
20 views
No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning

No More Guessing: a Verifiable Gradient Invers...

Machine Learning
Avatar
Francesco Diana
25 views
Load more