One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
Paper • 2605.29429 • Published • 2
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 19 hours ago
One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation upvoted a paper about 19 hours ago
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models upvoted a paper about 19 hours ago
FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit EncoderOrganizations
upvoted 3
papers about 19 hours ago
updated a
collection about 19 hours ago
upvoted 13
papers about 19 hours ago
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
Paper • 2605.30011 • Published • 6
When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
Paper • 2605.28181 • Published • 3
The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
Paper • 2605.29411 • Published • 2
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Paper • 2605.30514 • Published • 3
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Paper • 2605.30557 • Published • 6
SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
Paper • 2605.30329 • Published • 3
Count Anything
Paper • 2605.30846 • Published • 4
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
Paper • 2605.31455 • Published • 3
How can embedding models bind concepts?
Paper • 2605.31503 • Published • 6
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Paper • 2605.31170 • Published • 4
The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement
Paper • 2605.30888 • Published • 4
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
Paper • 2605.31433 • Published • 20
PEEK: Picking Essential frames via Efficient Knowledge distillation
Paper • 2605.31029 • Published • 16
commented a
paper about 19 hours ago
updated a
collection about 19 hours ago
upvoted a paper about 19 hours ago