RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Paper • 2605.10899 • Published • 70
AI & ML interests
Google ❤️ Open Source AI
Recent Activity
View all activity
Papers
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
gaotang
submitted a
paper to Daily Papers 2 days ago
Request: DOI
2
#13 opened 6 days ago
by 
SkyLeader123
access
1
#78 opened 5 days ago
by 
alparslankoc
Chat template for vLLM compatibility?
2
#8 opened 3 days ago
by 
vrdn23
minghaoyan
submitted a
paper to Daily Papers 3 days ago
Gemma4 is super slow on vllm docker , max to max 15 token per second only (4 X L4 GPU)
1
#102 opened 6 days ago
by 
vi-ajayb
hadamelino
submitted a
paper to Daily Papers 4 days ago
MaartenGr
updated 4
models 4 days ago
dxlong2000
submitted a
paper to Daily Papers 4 days ago
fix(chat_template): Emit multimodal placeholders in tool response content-parts
9
#38 opened 14 days ago
by 
harshaljanjani
GGUF available — Cerebellum v3 (11 GB, ablation-guided mixed-precision)
2
#37 opened 14 days ago
by 
deucebucket
Can't run Gemma4 locally
7
#6 opened 10 days ago
by 
polymathLTE
This model is so good, but the KV cache ruins it.
1
#100 opened 9 days ago
by 
UniversalLove333
galyona
authored 4
papers 8 days ago
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Paper • 2405.05904 • Published • 6
MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
Paper • 2505.24858 • Published • 17
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Paper • 2507.06261 • Published • 67
SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
Paper • 2509.07968 • Published • 14