-
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper • 2511.13254 • Published • 134 -
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Paper • 2511.14582 • Published • 17 -
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Paper • 2511.15248 • Published • 6
3hiuwoo
LilRain17
·
AI & ML interests
Embodied AI, Large Model
Recent Activity
updated
a collection
17 days ago
MMReasoning
updated
a collection
17 days ago
LLM
updated
a collection
17 days ago
Agent
Organizations
VLM
-
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Paper • 2511.11007 • Published • 15 -
Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
Paper • 2511.17487 • Published • 9 -
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 42
MMReasoning
-
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 91 -
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Paper • 2511.08577 • Published • 104 -
Experience-Guided Adaptation of Inference-Time Reasoning Strategies
Paper • 2511.11519 • Published • 3
benchmark
Agent
-
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
Paper • 2511.15705 • Published • 92 -
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Paper • 2511.13593 • Published • 24 -
OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists
Paper • 2511.16931 • Published • 6 -
General Agentic Memory Via Deep Research
Paper • 2511.18423 • Published • 157
LLM
-
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper • 2511.13254 • Published • 134 -
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Paper • 2511.14582 • Published • 17 -
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Paper • 2511.15248 • Published • 6
benchmark
VLM
-
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Paper • 2511.11007 • Published • 15 -
Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
Paper • 2511.17487 • Published • 9 -
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 42
Agent
-
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
Paper • 2511.15705 • Published • 92 -
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Paper • 2511.13593 • Published • 24 -
OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists
Paper • 2511.16931 • Published • 6 -
General Agentic Memory Via Deep Research
Paper • 2511.18423 • Published • 157
MMReasoning
-
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 91 -
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Paper • 2511.08577 • Published • 104 -
Experience-Guided Adaptation of Inference-Time Reasoning Strategies
Paper • 2511.11519 • Published • 3