Machine Learning

PaPi: Parallel Picard-Duhamel Integration for Fast Neuro-Spectral Architectures

PaPi: Parallel Picard-Duhamel Integration for ...

Machine Learning
Avatar
librarian
7 views
Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks

Binary Discrete Diffusion: Candidate-Set Diffu...

Machine Learning
Avatar
Rodrigo Casado Noguerales
5 views
The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It

The Shape of the DPO Hyperparameter Landscape:...

Machine Learning
Avatar
Hannan Mahadik
6 views
Near-Duplicate Image Selection Transfers Preferences in Vision-Language Models

Near-Duplicate Image Selection Transfers Prefe...

Machine Learning
Avatar
Jaeyoung Kim
7 views
Cross-Fitting for Neural Posterior Estimation

Cross-Fitting for Neural Posterior Estimation

Machine Learning
Avatar
librarian
5 views
recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models

recAMPLIFY: Large-Scale Pretraining of Recursi...

Machine Learning
Avatar
librarian
5 views
Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

Scaling Parameter-Efficient Fine-Tuning for Br...

Machine Learning
Avatar
Josh Ying
6 views
Parallel Language Models via Variational Decoding

Parallel Language Models via Variational Decoding

Machine Learning
Avatar
Felix Draxler
6 views
Kronecker Delta Rule for Long Context Linear Attention

Kronecker Delta Rule for Long Context Linear A...

Machine Learning
Avatar
Anamaria-Roberta Hartl
5 views
Text-to-Image Generative Modeling Without Language Pretraining

Text-to-Image Generative Modeling Without Lang...

Machine Learning
Avatar
Keshigeyan Chandrasegaran
5 views
Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization

Correctness-Dependent Asymmetric Target Distri...

Machine Learning
Avatar
librarian
4 views
Training-Free On-Policy Distillation

Training-Free On-Policy Distillation

Machine Learning
Avatar
Ge Liu
36 views
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths

Causal Integrated Gradients: Scalable Feature ...

Machine Learning
Avatar
librarian
36 views
PathFM: Fast Generative Forecasting of Multivariate Trajectories

PathFM: Fast Generative Forecasting of Multiva...

Machine Learning
Avatar
librarian
26 views
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning

Towards Continual Learning: Mitigating Forgett...

Machine Learning
Avatar
librarian
35 views
Rethinking Routing Exploration in Modern Mixture-of-Experts

Rethinking Routing Exploration in Modern Mixtu...

Machine Learning
Avatar
librarian
28 views
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

Librarian Agents: Training LLMs to Curate Long...

Machine Learning
Avatar
Anikait Singh
29 views
Memorilla: Latent Semantic Memory for LLMs

Memorilla: Latent Semantic Memory for LLMs

Machine Learning
Avatar
librarian
27 views
Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense

Multi-Reward Hacking: From Aggregation-Induced...

Machine Learning
Avatar
librarian
27 views
Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds

Transfer Learning in Bandits from Unknown Adap...

Machine Learning
Avatar
librarian
23 views
Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language Models

Linear Separability of Activation Representati...

Machine Learning
Avatar
m k
26 views
Generative Representation Learning for Scalable Latent Tokenization

Generative Representation Learning for Scalabl...

Machine Learning
Avatar
librarian
40 views
Continuum Attention

Continuum Attention

Machine Learning
Avatar
librarian
34 views
Your Transformer Is Secretly Elastic

Your Transformer Is Secretly Elastic

Machine Learning
Avatar
librarian
55 views
Reinforcement Learning via Advantage Guidance

Reinforcement Learning via Advantage Guidance

Machine Learning
Avatar
librarian
43 views
Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent

Rent-Seeking Language Models: Reward Models Se...

Machine Learning
Avatar
librarian
28 views
Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon

Memory-Efficient Subspace Optimization with Re...

Machine Learning
Avatar
librarian
26 views
Fast Rates for Offline Q-Learning with KL Regularization

Fast Rates for Offline Q-Learning with KL Regu...

Machine Learning
Avatar
librarian
25 views
Scaling Online Optimal Transport Minibatches for Flow Matching

Scaling Online Optimal Transport Minibatches f...

Machine Learning
Avatar
librarian
37 views
Model-Based Online Decision Making via Generative Trajectory Planning

Model-Based Online Decision Making via Generat...

Machine Learning
Avatar
librarian
40 views
SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection

SkillScaffold: Scaffolding Agentic Reinforceme...

Machine Learning
Avatar
librarian
43 views
Depth Memory

Depth Memory

Machine Learning
Avatar
librarian
32 views
Load more