Machine Learning

Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models

Ternary Mamba: Grouped Quantization-Aware Trai...

Machine Learning
Avatar
librarian
4 views
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs

SoftMoE: Soft Differentiable Routing for Mixtu...

Machine Learning
Avatar
librarian
4 views
Looped World Models

Looped World Models

Machine Learning
Avatar
librarian
6 views
Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?

Rethinking Dataset Distillation for Classifica...

Machine Learning
Avatar
Trisha Mittal
4 views
A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning

A Unified Causal-Origin Taxonomy of Distributi...

Machine Learning
Avatar
librarian
6 views
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting

HAMON: Passive Optical Sequence Mixing for Lon...

Machine Learning
Avatar
librarian
5 views
Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning

Your Privacy My Cloak: Backdoor Attacks on Dif...

Machine Learning
Avatar
librarian
6 views
Exact Posterior Score Estimation for Solving Linear Inverse Problems

Exact Posterior Score Estimation for Solving L...

Machine Learning
Avatar
librarian
5 views
Taming Curvature: Architecture Warm-Up for Stable Transformer Training

Taming Curvature: Architecture Warm-Up for Sta...

Machine Learning
Avatar
librarian
4 views
Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages

Beyond Weights and Gradients: A Taxonomy of Fe...

Machine Learning
Avatar
librarian
4 views
Proximal Policy Optimization for Amortized Discrete Sampling

Proximal Policy Optimization for Amortized Dis...

Machine Learning
Avatar
Anna Zykova-Myzina
6 views
MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

MosaicQuant: Inlier-Outlier Disaggregation for...

Machine Learning
Avatar
librarian
5 views
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training

ReQAT: Achieving Full-Precision Reasoning Accu...

Machine Learning
Avatar
librarian
5 views
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Dense Supervision, Sparse Updates: On the Spar...

Machine Learning
Avatar
librarian
34 views
The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning

The Stable Recovery Manifold: Geometric Princi...

Machine Learning
Avatar
librarian
31 views
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

Beyond the Commitment Boundary: Probing Epiphe...

Machine Learning
Avatar
Daniel Scalena
37 views
Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting

Existence Precedes Value: Joint Modeling of Ob...

Machine Learning
Avatar
librarian
38 views
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

A2D2: Fine-Tuning Any-Length Discrete Diffusio...

Machine Learning
Avatar
Sophia Tang
33 views
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

MaxProof: Scaling Mathematical Proof with Gene...

Machine Learning
Avatar
librarian
37 views
Learning with Simulators: No Regret in a Computationally Bounded World

Learning with Simulators: No Regret in a Compu...

Machine Learning
Avatar
Sasha Voitovych
28 views
Understanding Truncated Positional Encodings for Graph Neural Networks

Understanding Truncated Positional Encodings f...

Machine Learning
Avatar
librarian
29 views
The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics

The Standard Interpretable Model: A general th...

Machine Learning
Avatar
Pietro Barbiero
32 views
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Breaking Entropy Bounds: Accelerating RL Train...

Machine Learning
Avatar
librarian
30 views
On Subquadratic Architectures: From Applications to Principles

On Subquadratic Architectures: From Applicatio...

Machine Learning
Avatar
librarian
32 views
APPO: Agentic Procedural Policy Optimization

APPO: Agentic Procedural Policy Optimization

Machine Learning
Avatar
librarian
30 views
Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Redesign Mixture-of-Experts Routers with Manif...

Machine Learning
Avatar
Songhao Wu
35 views
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

Generalization Hacking: Models Can Game Reinfo...

Machine Learning
Avatar
librarian
28 views
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

EEVEE: Towards Test-time Prompt Learning in th...

Machine Learning
Avatar
Weixian Xu
48 views
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

A Unifying Lens on Supervised Fine-Tuning Thro...

Machine Learning
Avatar
Tong Xie
37 views
When to Align, When to Predict: A Phase Diagram for Multimodal Learning

When to Align, When to Predict: A Phase Diagra...

Machine Learning
Avatar
Ilay Kamai
34 views
K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

K-Forcing: Joint Next-K-Token Decoding via Pus...

Machine Learning
Avatar
librarian
32 views
CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference

CLP: Collocation-Length Prediction for Zero-Lo...

Machine Learning
Avatar
librarian
31 views
Load more