BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate Paper • 2604.25203 • Published 21 days ago • 8
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification Paper • 2604.14531 • Published Apr 16 • 7
Geometric Context Transformer for Streaming 3D Reconstruction Paper • 2604.14141 • Published Apr 15 • 21
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens Paper • 2604.04913 • Published Apr 6 • 12
KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs Paper • 2512.11851 • Published Dec 4, 2025 • 1
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios Paper • 2603.28130 • Published Mar 30 • 11
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Paper • 2404.03214 • Published Apr 4, 2024 • 3
VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs Paper • 2512.21194 • Published Dec 24, 2025
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published Mar 27 • 144
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published Mar 27 • 144
Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders Paper • 2603.19209 • Published Mar 19 • 5
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning Paper • 2603.14482 • Published Mar 15 • 35
XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision Paper • 2601.21688 • Published Jan 29
Revealing Subtle Phenotypes in Small Microscopy Datasets Using Latent Diffusion Models Paper • 2502.09665 • Published Feb 12, 2025
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections Paper • 2603.12180 • Published Mar 12 • 65