Elijah Harris

gracenelson's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 2 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published 11 days ago • 157

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Paper • 2606.25621 • Published 15 days ago • 22

upvoted a paper 18 days ago

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Paper • 2606.18322 • Published 23 days ago • 17

upvoted a paper 29 days ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published Jun 3 • 126

upvoted 3 papers about 1 month ago

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

Paper • 2605.29429 • Published May 28 • 8

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Paper • 2601.07525 • Published May 28 • 10

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Paper • 2605.20910 • Published May 20 • 29

upvoted 3 papers about 2 months ago

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

Paper • 2605.19932 • Published May 19 • 7

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

Paper • 2605.12882 • Published May 13 • 274

Position: LLM Inference Should Be Evaluated as Energy-to-Token Production

Paper • 2605.11733 • Published May 12 • 3

upvoted 2 papers 2 months ago

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks

Paper • 2604.27818 • Published Apr 30 • 5

From Context to Skills: Can Language Models Learn from Context Skillfully?

Paper • 2604.27660 • Published May 3 • 171

upvoted 8 papers 3 months ago

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 245

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Paper • 2604.07429 • Published Apr 8 • 123

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 248

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published Apr 9 • 295

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 265

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published Apr 8 • 329

Emergent Compositional Communication for Latent World Properties

Paper • 2604.03266 • Published Mar 18 • 7

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published Mar 27 • 365