InfoSynth: Information-Guided Benchmark Synthesis for LLMs Paper • 2601.00575 • Published 7 days ago • 2
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning Paper • 2512.16909 • Published 22 days ago • 1
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit Paper • 2512.10092 • Published 30 days ago • 2
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks Paper • 2305.08842 • Published May 15, 2023
Training Neural Networks from Scratch with Parallel Low-Rank Adapters Paper • 2402.16828 • Published Feb 26, 2024 • 3
System identification of neural systems: If we got it right, would we know? Paper • 2302.06677 • Published Feb 13, 2023
Training the Untrainable: Introducing Inductive Bias via Representational Alignment Paper • 2410.20035 • Published Oct 26, 2024
Fast Simultaneous Training of Generalized Linear Models (FaSTGLZ) Paper • 1307.8430 • Published Jul 31, 2013
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models Paper • 2505.24133 • Published May 30, 2025 • 2
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation Paper • 2312.16610 • Published Dec 27, 2023
DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering Paper • 2507.11527 • Published Jul 15, 2025 • 32
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations Paper • 2410.02762 • Published Oct 3, 2024 • 9
Learning Adaptive Parallel Reasoning with Language Models Paper • 2504.15466 • Published Apr 21, 2025 • 44