Machine Learning

Tight Sample Complexity of Transformers

Tight Sample Complexity of Transformers

Machine Learning
Avatar
librarian
10 views
Rethinking the Divergence Regularization in LLM RL

Rethinking the Divergence Regularization in LLM RL

Machine Learning
Avatar
librarian
3 views
Muon Learns More Robust and Transferable Features than Adam

Muon Learns More Robust and Transferable Featu...

Machine Learning
Avatar
Fengzhuo Zhang
10 views
Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems

Graph Mamba Operator: A Latent Simulator for I...

Machine Learning
Avatar
librarian
10 views
In-Context Learning for Latent Space Bayesian Optimization

In-Context Learning for Latent Space Bayesian ...

Machine Learning
Avatar
librarian
10 views
Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

Algorithm for Contextual Queueing Bandits with...

Machine Learning
Avatar
Seoungbin Bae
4 views
Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Beyond Linear Activation Steering: Invertible ...

Machine Learning
Avatar
librarian
5 views
OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework

OrderDP: A Theoretically Guaranteed Lossless D...

Machine Learning
Avatar
librarian
5 views
End-to-End Subgraph Detection with GraphDETR

End-to-End Subgraph Detection with GraphDETR

Machine Learning
Avatar
librarian
21 views
The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning

The Post-GCN Decade Revisited: Curvature-Strat...

Machine Learning
Avatar
Shuo Wang
26 views
Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving

Tangram: Unlocking Non-Uniform KV Cache for Ef...

Machine Learning
Avatar
librarian
31 views
Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

Plug-and-Play Guidance for Discrete Diffusion ...

Machine Learning
Avatar
librarian
27 views
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss

Double Preconditioning (DoPr): Optimization fo...

Machine Learning
Avatar
Thomas Zhanga
28 views
TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

TailLoR: Protecting Principal Components in Pa...

Machine Learning
Avatar
librarian
28 views
Regret Minimization with Adaptive Opponents in Repeated Games

Regret Minimization with Adaptive Opponents in...

Machine Learning
Avatar
librarian
28 views
RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

RREDCoT: Segment-Level Reward Redistribution f...

Machine Learning
Avatar
librarian
19 views
Pretraining Recurrent Networks without Recurrence

Pretraining Recurrent Networks without Recurrence

Machine Learning
Avatar
librarian
38 views
Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning

Deep Embedded Multiplicative DMD for Algebra-P...

Machine Learning
Avatar
Kelan Gray
27 views
Reinforcement Learning from Rich Feedback with Distributional DAgger

Reinforcement Learning from Rich Feedback with...

Machine Learning
Avatar
librarian
29 views
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

STRIDE: Training Data Attribution via Sparse R...

Machine Learning
Avatar
librarian
39 views
Neuron Populations Exhibit Divergent Selectivity with Scale

Neuron Populations Exhibit Divergent Selectivi...

Machine Learning
Avatar
Amil Dravid
28 views
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Skill-RM: Unifying Heterogeneous Evaluation Cr...

Machine Learning
Avatar
librarian
31 views
Dynamic Short Convolutions Improve Transformers

Dynamic Short Convolutions Improve Transformers

Machine Learning
Avatar
librarian
30 views
q0: Primitives for Hyper-Epoch Pretraining

q0: Primitives for Hyper-Epoch Pretraining

Machine Learning
Avatar
librarian
30 views
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

Language Models Need Sleep: Learning to Self-M...

Machine Learning
Avatar
Ali Behrouz
27 views
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression

Rethinking the Role of Tensor Decompositions i...

Machine Learning
Avatar
librarian
30 views
Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

Training a Predictive Coding Network on ImageN...

Machine Learning
Avatar
librarian
34 views
When Model Merging Breaks Routing: Training-Free Calibration for MoE

When Model Merging Breaks Routing: Training-Fr...

Machine Learning
Avatar
Xiaojun Quan
31 views
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

KVarN: Variance-Normalized KV-Cache Quantizati...

Machine Learning
Avatar
librarian
36 views
CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery

CauTion: Knowing When to Trust LLMs for Ensemb...

Machine Learning
Avatar
librarian
30 views
Measurement Geometry and Design for Trustworthy Generative Inverse Problems

Measurement Geometry and Design for Trustworth...

Machine Learning
Avatar
librarian
32 views
Drifting Preference Optimization for One-Step Generative Models

Drifting Preference Optimization for One-Step ...

Machine Learning
Avatar
librarian
36 views
Load more