Show, Don't Tell: Morphing Latent Reasoning into Image Generation
Paper
•
2602.02227
•
Published
•
10
•
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commented on
a paper
about 19 hours ago
Show, Don't Tell: Morphing Latent Reasoning into Image Generation
commented on
a paper
about 19 hours ago
Enhancing Multi-Image Understanding through Delimiter Token Scaling
commented on
a paper
about 19 hours ago
On the Limits of Layer Pruning for Generative Reasoning in LLMs
Organizations
commented
20
papers
about 19 hours ago
Enhancing Multi-Image Understanding through Delimiter Token Scaling
Paper
•
2602.01984
•
Published
•
5
•
2
On the Limits of Layer Pruning for Generative Reasoning in LLMs
Paper
•
2602.01997
•
Published
•
2
•
2
Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
Paper
•
2602.01538
•
Published
•
15
•
3
YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation
Paper
•
2602.00168
•
Published
•
1
•
2
VoxServe: Streaming-Centric Serving System for Speech Language Models
Paper
•
2602.00269
•
Published
•
6
•
2
Clipping-Free Policy Optimization for Large Language Models
Paper
•
2601.22801
•
Published
•
1
•
2
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
Paper
•
2602.02338
•
Published
•
38
•
2
RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment
Paper
•
2602.00682
•
Published
•
1
•
2
The Necessity of a Unified Framework for LLM-Based Agent Evaluation
Paper
•
2602.03238
•
Published
•
1
•
2
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
Paper
•
2602.03845
•
Published
•
24
•
3
MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning
Paper
•
2602.03320
•
Published
•
2
•
2
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
Paper
•
2602.03139
•
Published
•
36
•
3
Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
Paper
•
2602.03086
•
Published
•
14
•
2
WideSeek: Advancing Wide Research via Multi-Agent Scaling
Paper
•
2602.02636
•
Published
•
13
•
4
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Paper
•
2602.03411
•
Published
•
33
•
2
SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
Paper
•
2602.02419
•
Published
•
4
•
2
Unified Personalized Reward Model for Vision Generation
Paper
•
2602.02380
•
Published
•
17
•
2
Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation
Paper
•
2602.03619
•
Published
•
23
•
2
MARS: Modular Agent with Reflective Search for Automated AI Research
Paper
•
2602.02660
•
Published
•
54
•
4