Machine Learning

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

How Data Shapes RoPE Frequency Usage: From Pos...

Machine Learning
Avatar
librarian
5 views
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Single-Rollout Asynchronous Optimization for A...

Machine Learning
Avatar
librarian
4 views
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning

Agon: Competitive Cross-Model RL with Implicit...

Machine Learning
Avatar
Vladislav Beliaev
4 views
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

Selective Timestep Weighting and Advantage-Bas...

Machine Learning
Avatar
Eric Zhu
4 views
The Key to Going Linear: Analysis-Driven Transformer Linearization

The Key to Going Linear: Analysis-Driven Trans...

Machine Learning
Avatar
librarian
4 views
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

Graph Convolutional Attention: A Spectral Pers...

Machine Learning
Avatar
librarian
22 views
Canopy: A Heterograph Foundation Model for Metabolic Engineering

Canopy: A Heterograph Foundation Model for Met...

Machine Learning
Avatar
librarian
7 views
Physics-Informed Neural Embeddings of PDE Solution Families

Physics-Informed Neural Embeddings of PDE Solu...

Machine Learning
Avatar
Leonid Sarieddine
7 views
Quantitative Gaussian-Process limits of Tensor Programs

Quantitative Gaussian-Process limits of Tensor...

Machine Learning
Avatar
librarian
7 views
TILDE: TILt-based Distributional Erasure for Concept Unlearning

TILDE: TILt-based Distributional Erasure for C...

Machine Learning
Avatar
librarian
6 views
CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

CompactionRL: Reinforcement Learning with Cont...

Machine Learning
Avatar
librarian
81 views
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials

Beyond Adam: SOAP and Muon for Faster, Label-E...

Machine Learning
Avatar
librarian
19 views
DecompRL: Solving Harder Problems by Learning Modular Code Generation

DecompRL: Solving Harder Problems by Learning ...

Machine Learning
Avatar
librarian
19 views
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Neuron-Aware Data Selection for Annotation-Fre...

Machine Learning
Avatar
librarian
18 views
DemoPSD: Disagreement-Modulated Policy Self-Distillation

DemoPSD: Disagreement-Modulated Policy Self-Di...

Machine Learning
Avatar
Yunhe Li
51 views
Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Program-as-Weights: A Programming Paradigm for...

Machine Learning
Avatar
librarian
19 views
HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures

HERMES: A Multi-Granularity Labeling Substrate...

Machine Learning
Avatar
librarian
20 views
Generalization in offline RL: The structure is more important than the amount of pessimism

Generalization in offline RL: The structure is...

Machine Learning
Avatar
Max Weltevrede
16 views
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

One More Time: Revisiting Neural Quantum State...

Machine Learning
Avatar
Juan Agustín Duque
16 views
A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data

A Lightweight Self-Supervised Learning Framewo...

Machine Learning
Avatar
librarian
41 views
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations

Right in the Right Way: LM Training with Verif...

Machine Learning
Avatar
Mehul Damani
29 views
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming

TiRex-2: Generalizing TiRex to Multivariate Da...

Machine Learning
Avatar
librarian
21 views
Language-Critique Imitation Learning from Suboptimal Demonstrations

Language-Critique Imitation Learning from Subo...

Machine Learning
Avatar
librarian
23 views
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling

QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling

Machine Learning
Avatar
librarian
22 views
Neural Certificate Pricing for Combinatorial Optimization Problems

Neural Certificate Pricing for Combinatorial O...

Machine Learning
Avatar
librarian
23 views
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Is One Layer Enough? Training A Single Transfo...

Machine Learning
Avatar
Zijian Zhang
23 views
Signed-Permutation Coordinate Transport for RMSNorm Transformers

Signed-Permutation Coordinate Transport for RM...

Machine Learning
Avatar
librarian
26 views
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Bridging the Gap Between Latent and Explicit R...

Machine Learning
Avatar
librarian
154 views
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

SemRF: A Semantic Reference Frame for Residual...

Machine Learning
Avatar
librarian
29 views
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

QVal: Cheaply Evaluating Dense Supervision Sig...

Machine Learning
Avatar
Sergio Hernández-Gutiérrez
34 views
Calibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language Models

Calibration, Not Compilation: Detecting and Re...

Machine Learning
Avatar
Jian Xu
27 views
TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

TabPATE: Differentially Private Tabular In-Con...

Machine Learning
Avatar
Dariush Wahdany
24 views
Load more