Machine Learning

Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts

Latent Prototype Routing: Achieving Near-Perfe...

Machine Learning
Avatar
librarian
1 view
Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference

Scalable Bayesian Low-Rank Adaptation of Large...

Machine Learning
Avatar
librarian
0 views
DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster

DiLoCoX: A Low-Communication Large-Scale Train...

Machine Learning
Avatar
librarian
0 views
Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

Where to find Grokking in LLM Pretraining? Mon...

Machine Learning
Avatar
Ziyue Li
0 views
mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale

mTSBench: Benchmarking Multivariate Time Serie...

Machine Learning
Avatar
librarian
1 view
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

LoX: Low-Rank Extrapolation Robustifies LLM Sa...

Machine Learning
Avatar
librarian
16 views
CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization

CAWR: Corruption-Averse Advantage-Weighted Reg...

Machine Learning
Avatar
Ranting Hu
5 views
Over-squashing in Spatiotemporal Graph Neural Networks

Over-squashing in Spatiotemporal Graph Neural ...

Machine Learning
Avatar
librarian
8 views
AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning

AutoRule: Reasoning Chain-of-thought Extracted...

Machine Learning
Avatar
Tevin Wang
9 views
RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation

RePCS: Diagnosing Data Memorization in LLM-Pow...

Machine Learning
Avatar
librarian
5 views
Memory-Efficient Differentially Private Training with Gradient Random Projection

Memory-Efficient Differentially Private Traini...

Machine Learning
Avatar
librarian
5 views
Dense SAE Latents Are Features, Not Bugs

Dense SAE Latents Are Features, Not Bugs

Machine Learning
Avatar
librarian
9 views
Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning

Train Once, Forget Precisely: Anchored Optimiz...

Machine Learning
Avatar
librarian
5 views
Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization

Expressive Score-Based Priors for Distribution...

Machine Learning
Avatar
librarian
5 views
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

TGDPO: Harnessing Token-Level Reward Guidance ...

Machine Learning
Avatar
Mingkang Zhu
6 views
Towards Desiderata-Driven Design of Visual Counterfactual Explainers

Towards Desiderata-Driven Design of Visual Cou...

Machine Learning
Avatar
librarian
5 views
On the Hardness of Bandit Learning

On the Hardness of Bandit Learning

Machine Learning
Avatar
librarian
4 views
VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Models

VideoPDE: Unified Generative PDE Solving via V...

Machine Learning
Avatar
librarian
14 views
Flexible-length Text Infilling for Discrete Diffusion Models

Flexible-length Text Infilling for Discrete Di...

Machine Learning
Avatar
librarian
9 views
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

Diagnosing and Improving Diffusion Models by E...

Machine Learning
Avatar
librarian
13 views
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

TimeMaster: Training Time-Series Multimodal LL...

Machine Learning
Avatar
Junru Zhang
17 views
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs

Attribution-guided Pruning for Compression, Ci...

Machine Learning
Avatar
librarian
8 views
Discrete Diffusion in Large Language and Multimodal Models: A Survey

Discrete Diffusion in Large Language and Multi...

Machine Learning
Avatar
librarian
11 views
Rethinking Losses for Diffusion Bridge Samplers

Rethinking Losses for Diffusion Bridge Samplers

Machine Learning
Avatar
librarian
28 views
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models

GUARD: Guided Unlearning and Retention via Dat...

Machine Learning
Avatar
librarian
40 views
Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods

Understanding In-Context Learning on Structure...

Machine Learning
Avatar
librarian
48 views
Self-Adapting Language Models

Self-Adapting Language Models

Machine Learning
Avatar
Adam Zweiger
46 views
Farseer: A Refined Scaling Law in Large Language Models

Farseer: A Refined Scaling Law in Large Langua...

Machine Learning
Avatar
librarian
40 views
Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning

Principled Approaches for Extending Neural Arc...

Machine Learning
Avatar
librarian
41 views
Canonical Latent Representations in Conditional Diffusion Models

Canonical Latent Representations in Conditiona...

Machine Learning
Avatar
librarian
51 views
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Multiverse: Your Language Models Secretly Deci...

Machine Learning
Avatar
Xinyu Yang
54 views
Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Flipping Against All Odds: Reducing LLM Coin F...

Machine Learning
Avatar
librarian
52 views
Load more