AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace Paper β’ 2608.23740 β’ Published Aug 24 β’ 8
Automata from Agent Traces: Failure and Next-Step Prediction Paper β’ 2608.23670 β’ Published Aug 24 β’ 6
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features Paper β’ 2602.10437 β’ Published Feb 12 β’ 2
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment Paper β’ 2607.26981 β’ Published Jul 29 β’ 2
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects Paper β’ 2607.20596 β’ Published Jul 22 β’ 3
pplx-embed Collection Diffusion-Pretrained Dense and Contextual Embeddings β’ 12 items β’ Updated Sep 4 β’ 103
CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection Paper β’ 2508.12535 β’ Published Aug 18, 2025 β’ 2
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies Paper β’ 2506.17673 β’ Published Jun 21, 2025 β’ 7
Distil-Whisper Models Collection The first version of the Distil-Whisper models released with the Distil-Whisper paper. β’ 4 items β’ Updated Mar 21, 2024 β’ 36
Retentive Network: A Successor to Transformer for Large Language Models Paper β’ 2307.08621 β’ Published Jul 17, 2023 β’ 173
YaRN: Efficient Context Window Extension of Large Language Models Paper β’ 2309.00071 β’ Published Aug 31, 2023 β’ 85