Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
Paper • 2607.16204 • Published • 7
AI & ML interests
LLM Evaluation
Recent Activity
Papers
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Add reinforcement-learning task category, paper and GitHub links
1
#2 opened 9 days ago
by 
nielsr
DarshanDeshpande
submitted a
paper to Daily Papers 9 days ago
DarshanDeshpande
published a
dataset 2 months ago
DarshanDeshpande
updated a
dataset 2 months ago
akkikiki
authored 2
papers 4 months ago
DarshanDeshpande
submitted a
paper to Daily Papers 6 months ago
mvasil
authored 5
papers 7 months ago
HandsOff: Labeled Dataset Generation With No Additional Human Annotations
Paper • 2212.12645 • Published • 1
Why do These Match? Explaining the Behavior of Image Similarity Models
Paper • 1905.10797 • Published • 1
OutfitTransformer: Learning Outfit Representations for Fashion Recommendation
Paper • 2204.04812 • Published • 1
Learning Type-Aware Embeddings for Fashion Compatibility
Paper • 1803.09196 • Published • 2
Learning Similarity Conditions Without Explicit Supervision
Paper • 1908.08589 • Published • 1
akkikiki
authored a
paper 9 months ago
DarshanDeshpande
authored a
paper 10 months ago
DarshanDeshpande
authored a
paper about 1 year ago
anandnk24
authored 5
papers over 1 year ago
Lynx: An Open Source Hallucination Evaluation Model
Paper • 2407.08488 • Published • 1
SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
Paper • 2311.08370 • Published
FinanceBench: A New Benchmark for Financial Question Answering
Paper • 2311.11944 • Published
GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking
Paper • 2412.14140 • Published • 1
Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning
Paper • 2503.19193 • Published • 1