Machine Learning

When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence

When Flat Minima Fail: Characterizing INT4 Qua...

Machine Learning
Avatar
librarian
0 views
Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning

Blazing the trails before beating the path: Sa...

Machine Learning
Avatar
Jean-Bastien Grill
0 views
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

LLMs Gaming Verifiers: RLVR can Lead to Reward...

Machine Learning
Avatar
librarian
1 view
MambaSL: Exploring Single-Layer Mamba for Time Series Classification

MambaSL: Exploring Single-Layer Mamba for Time...

Machine Learning
Avatar
Yoo-Min Jung
0 views
Momentum Further Constrains Sharpness at the Edge of Stochastic Stability

Momentum Further Constrains Sharpness at the E...

Machine Learning
Avatar
Arseniy Andreyev
20 views
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

LongCoT: Benchmarking Long-Horizon Chain-of-Th...

Machine Learning
Avatar
librarian
24 views
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space

From $P(y|x)$ to $P(y)$: Investigating Reinfor...

Machine Learning
Avatar
Yuqiao Tan
28 views
HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark

HINTBench: Horizon-agent Intrinsic Non-attack ...

Machine Learning
Avatar
librarian
14 views
Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation

Provably Efficient Offline-to-Online Value Ada...

Machine Learning
Avatar
librarian
14 views
MAny: Merge Anything for Multimodal Continual Instruction Tuning

MAny: Merge Anything for Multimodal Continual ...

Machine Learning
Avatar
Zijian Gao
17 views
Parcae: Scaling Laws For Stable Looped Language Models

Parcae: Scaling Laws For Stable Looped Languag...

Machine Learning
Avatar
librarian
17 views
An Optimal Sauer Lemma Over $k$-ary Alphabets

An Optimal Sauer Lemma Over $k$-ary Alphabets

Machine Learning
Avatar
librarian
9 views
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

Lightning OPD: Efficient Post-Training for Lar...

Machine Learning
Avatar
librarian
9 views
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Rethinking On-Policy Distillation of Large Lan...

Machine Learning
Avatar
librarian
7 views
KumoRFM-2: Scaling Foundation Models for Relational Learning

KumoRFM-2: Scaling Foundation Models for Relat...

Machine Learning
Avatar
librarian
9 views
Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory

Understanding and Improving Continuous Adversa...

Machine Learning
Avatar
librarian
9 views
SCNO: Spiking Compositional Neural Operator -- Towards a Neuromorphic Foundation Model for Nuclear PDE Solving

SCNO: Spiking Compositional Neural Operator --...

Machine Learning
Avatar
Samrendra Roy
10 views
KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective

KL Divergence Between Gaussians: A Step-by-Ste...

Machine Learning
Avatar
librarian
9 views
Layerwise Dynamics for In-Context Classification in Transformers

Layerwise Dynamics for In-Context Classificati...

Machine Learning
Avatar
librarian
10 views
Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning

Fairness is Not Flat: Geometric Phase Transiti...

Machine Learning
Avatar
librarian
12 views
Towards Autonomous Mechanistic Reasoning in Virtual Cells

Towards Autonomous Mechanistic Reasoning in Vi...

Machine Learning
Avatar
librarian
13 views
A Mechanistic Analysis of Looped Reasoning Language Models

A Mechanistic Analysis of Looped Reasoning Lan...

Machine Learning
Avatar
Hugh Blayney
11 views
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators

Solving Physics Olympiad via Reinforcement Lea...

Machine Learning
Avatar
librarian
11 views
WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting

WaveMoE: A Wavelet-Enhanced Mixture-of-Experts...

Machine Learning
Avatar
librarian
9 views
CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

CodeQuant: Unified Clustering and Quantization...

Machine Learning
Avatar
librarian
10 views
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs

IceCache: Memory-efficient KV-cache Management...

Machine Learning
Avatar
Yuzhen Mao
8 views
Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks

Topology-Aware PAC-Bayesian Generalization Ana...

Machine Learning
Avatar
Xinping Yi
8 views
SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization

SOLAR: Communication-Efficient Model Adaptatio...

Machine Learning
Avatar
Seyed Mahmoud Sajjadi Mohammadabadi
18 views
TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis

TTVS: Boosting Self-Exploring Reinforcement Le...

Machine Learning
Avatar
librarian
29 views
KV Cache Offloading for Context-Intensive Tasks

KV Cache Offloading for Context-Intensive Tasks

Machine Learning
Avatar
librarian
19 views
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

What Drives Representation Steering? A Mechani...

Machine Learning
Avatar
librarian
31 views
Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models

Dead Weights, Live Signals: Feedforward Graphs...

Machine Learning
Avatar
Marcus Armstrong
39 views
Load more