MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Paper
•
2511.11793
•
Published
•
159
Kala KB
Kaytheist
AI & ML interests
None yet
Recent Activity
liked
a model
about 17 hours ago
facebook/sam3
liked
a model
about 18 hours ago
open-thoughts/OpenThinker-Agent-v1
Organizations
None yet
upvoted
a
paper
2 days ago
upvoted
6
articles
3 days ago
Article
Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement
•
11
Article
Understanding Model Reasoning Through Thought Anchors: A Comparative Study of Qwen3 and DeepSeek-R1
•
5
Article
AutoThink: Adaptive Reasoning for Large Language Models
•
7
Article
System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience
•
21
Article
Towards Open Evolutionary Agents
•
20
Article
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
•
51
upvoted
13
papers
3 days ago
Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
Paper
•
2512.04844
•
Published
•
4
ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
Paper
•
2512.05110
•
Published
•
3
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
Paper
•
2512.01803
•
Published
•
4
EgoLCD: Egocentric Video Generation with Long Context Diffusion
Paper
•
2512.04515
•
Published
•
5
FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring
Paper
•
2512.04390
•
Published
•
7
BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
Paper
•
2512.05076
•
Published
•
7
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
Paper
•
2511.22826
•
Published
•
7
SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization
Paper
•
2512.02631
•
Published
•
7
Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models
Paper
•
2512.04981
•
Published
•
7
Generative Neural Video Compression via Video Diffusion Prior
Paper
•
2512.05016
•
Published
•
8
LATTICE: Democratize High-Fidelity 3D Generation at Scale
Paper
•
2512.03052
•
Published
•
9
Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
Paper
•
2512.04356
•
Published
•
9
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
Paper
•
2512.04220
•
Published
•
11