lecture-review

3 posts

paper-review

19 posts

← All Categories

UOS 2025 Spring

3 posts

3d-generation

3 posts

emotion-mllm

2 posts

spatial-reasoning

5 posts

vision-language

9 posts

← Back

• 2026-01-01
  Lecture 14: Reasoning
• 2025-12-28
  Lecture 11: High-Resolution, High-Performing LVLMs
• 2025-12-26
  Lecture 10: Large Vision Language Models (LVLMs)

• 2026-05-04
  World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
• 2026-04-29
  When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
• 2026-04-29
  SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
• 2026-04-28
  MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
• 2026-04-27
  SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

• 2026-03-30
  InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
• 2026-03-30
  Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
• 2026-02-22
  BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
• 2026-02-22
  Flamingo: a Visual Language Model for Few-Shot Learning
• 2026-02-22
  [MiniGPT-4] Enhancing Vision-Language Understanding with Advanced Large Language Models
• 2026-02-10
  Improved Baselines with Visual Instruction Tuning (LLaVA-1.5)
• 2026-01-31
  Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
• 2026-01-05
  Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
• 2025-08-29
  LLaVA: Large Language and Vision Assistant

• 2025-11-25
  Uni3D: Exploring Unified 3D Representation at Scale
• 2025-11-24
  ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
• 2025-11-16
  Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

• 2025-09-01
  Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models
• 2024-11-20
  EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning