From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
Paper • 2605.09591 • Published • 1
Urro PRO
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 15 hours ago
From Pixels to Concepts: Do Segmentation Models Understand What They Segment? upvoted a paper about 15 hours ago
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs updated a collection about 15 hours ago
WTF GENIUS PAPERSOrganizations
upvoted 6
papers about 15 hours ago
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
Paper • 2605.08737 • Published • 2
FeatCal: Feature Calibration for Post-Merging Models
Paper • 2605.13030 • Published • 4
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Paper • 2605.12825 • Published • 7
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Paper • 2605.13511 • Published • 27
Qwen-Image-VAE-2.0 Technical Report
Paper • 2605.13565 • Published • 42
upvoted 9
papers 1 day ago
Reliable Chain-of-Thought via Prefix Consistency
Paper • 2605.07654 • Published • 1
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Paper • 2605.05630 • Published • 10
Debiased Model-based Representations for Sample-efficient Continuous Control
Paper • 2605.11711 • Published • 8
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
Paper • 2605.12460 • Published • 15
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Paper • 2605.10977 • Published • 9
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
Paper • 2605.11011 • Published • 9
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Paper • 2605.07579 • Published • 13
Teaching Language Models to Think in Code
Paper • 2605.07237 • Published • 22
δ-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 101
upvoted 3
articles 3 days ago
Article
You do the work. Big Tech takes the model.
urroxyz
• • 3 Article
They Said It Couldn’t Be Done
Pclanglais
• • 91 Article
Releasing the largest multilingual open pretraining dataset
Pclanglais
• • 107 upvoted a paper 3 days ago
upvoted a paper 4 days ago