Machine Learning

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Improving Data Efficiency for LLM Reinforcemen...

Machine Learning
Avatar
Yifan Sun
2 views
Exploring Diffusion Transformer Designs via Grafting

Exploring Diffusion Transformer Designs via Gr...

Machine Learning
Avatar
librarian
17 views
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

MesaNet: Sequence Modeling by Locally Optimal ...

Machine Learning
Avatar
Johannes von Oswald
15 views
Kinetics: Rethinking Test-Time Scaling Laws

Kinetics: Rethinking Test-Time Scaling Laws

Machine Learning
Avatar
librarian
20 views
Inference-Time Hyper-Scaling with KV Cache Compression

Inference-Time Hyper-Scaling with KV Cache Com...

Machine Learning
Avatar
librarian
16 views
MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures

MACS: Multi-Agent Reinforcement Learning for O...

Machine Learning
Avatar
librarian
16 views
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Advancing Multimodal Reasoning: From Optimized...

Machine Learning
Avatar
librarian
18 views
Horizon Reduction Makes RL Scalable

Horizon Reduction Makes RL Scalable

Machine Learning
Avatar
librarian
19 views
OpenThoughts: Data Recipes for Reasoning Models

OpenThoughts: Data Recipes for Reasoning Models

Machine Learning
Avatar
librarian
18 views
A Few Moments Please: Scalable Graphon Learning via Moment Matching

A Few Moments Please: Scalable Graphon Learnin...

Machine Learning
Avatar
librarian
18 views
Rectified Flows for Fast Multiscale Fluid Flow Modeling

Rectified Flows for Fast Multiscale Fluid Flow...

Machine Learning
Avatar
librarian
18 views
How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment

How Explanations Leak the Decision Logic: Stea...

Machine Learning
Avatar
Bin Ma
18 views
Not All Tokens Are Meant to Be Forgotten

Not All Tokens Are Meant to Be Forgotten

Machine Learning
Avatar
librarian
19 views
Provable Reinforcement Learning from Human Feedback with an Unknown Link Function

Provable Reinforcement Learning from Human Fee...

Machine Learning
Avatar
librarian
26 views
Zero-Shot Time Series Forecasting with Covariates via In-Context Learning

Zero-Shot Time Series Forecasting with Covaria...

Machine Learning
Avatar
librarian
24 views
StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

StreamBP: Memory-Efficient Exact Backpropagati...

Machine Learning
Avatar
librarian
24 views
PoLAR: Polar-Decomposed Low-Rank Adapter Representation

PoLAR: Polar-Decomposed Low-Rank Adapter Repre...

Machine Learning
Avatar
librarian
24 views
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds

Retrieval-Augmented Generation as Noisy In-Con...

Machine Learning
Avatar
librarian
24 views
MuLoCo: Muon is a practical inner optimizer for DiLoCo

MuLoCo: Muon is a practical inner optimizer fo...

Machine Learning
Avatar
librarian
55 views
Global optimization of graph acquisition functions for neural architecture search

Global optimization of graph acquisition funct...

Machine Learning
Avatar
Calvin Tsay
50 views
Model Immunization from a Condition Number Perspective

Model Immunization from a Condition Number Per...

Machine Learning
Avatar
librarian
49 views
AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

AMBER: Adaptive Mesh Generation by Iterative M...

Machine Learning
Avatar
librarian
47 views
Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?

Distortion of AI Alignment: Does Preference Op...

Machine Learning
Avatar
Paul Go¨lz
48 views
Continuous Chain of Thought Enables Parallel Exploration and Reasoning

Continuous Chain of Thought Enables Parallel E...

Machine Learning
Avatar
librarian
47 views
Learning Compositional Functions with Transformers from Easy-to-Hard Data

Learning Compositional Functions with Transfor...

Machine Learning
Avatar
librarian
46 views
Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

Knowledge Insulating Vision-Language-Action Mo...

Machine Learning
Avatar
librarian
47 views
REOrdering Patches Improves Vision Models

REOrdering Patches Improves Vision Models

Machine Learning
Avatar
librarian
46 views
Differential Information: An Information-Theoretic Perspective on Preference Optimization

Differential Information: An Information-Theor...

Machine Learning
Avatar
librarian
45 views
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

The Entropy Mechanism of Reinforcement Learnin...

Machine Learning
Avatar
librarian
48 views
Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

Position: Uncertainty Quantification Needs Rea...

Machine Learning
Avatar
librarian
48 views
Geometric Hyena Networks for Large-scale Equivariant Learning

Geometric Hyena Networks for Large-scale Equiv...

Machine Learning
Avatar
librarian
44 views
On Learning Verifiers for Chain-of-Thought Reasoning

On Learning Verifiers for Chain-of-Thought Rea...

Machine Learning
Avatar
Maria-Florina Balcan
48 views
Load more