Lecture 2 : Vision-Language landscape before Transformer + Pre-training
Lecturer: Aishwarya Agrawal
Slides (pdf, keynote)

Lecture 4: Shortcomings of Vision-Language models and Open Challenges
Lecturer: Aishwarya Agrawal
Slides (pdf, keynote)

Lecture 5: Image captioning

Review Paper

Paper Presentation 1: Image Captioning - Part 1 Slides

Paper Presentation 2: Image Captioning - Part 2 Slides

Project Presentation 1: Multimodal Curriculum Learning for Humanoid Loco-Manipulation Slides

Project Presentation 2: HORUS EYE - Language as Dynamic Attention for Emergency Visual Analysis Slides

Lecture 6: Visual Question Answering: Datasets

Review Paper

Paper Presentation 1: Visual Question Answering - Part 1 Slides

Paper Presentation 2: Visual Question Answering - Part 2 Slides

Project Presentation 1: Gap between generative and discriminative visual representations Slides

Project Presentation 2: Does Test-Time Scaling on Visual Thinking Models Enhance Object Counting Capabilities? Slides

Lecture 7:  Visual Dialog: Datasets and Models

Review Paper

Paper Presentation 1: Visual Dialog - Part 1 Slides

Project Presentation 1: Beyond Spatial QA: Cross-Viewpoint Relational Invariance in VLMs Slides

Project Presentation 2: Sketch2UML - Draw to Formalize Slides

Lecture 8:  Interpretability and Explainability

Review Paper

Paper Presentation 1: Interpretability and Explainability - Part 1 Slides

Paper Presentation 2: Interpretability and Explainability - Part 2 Slides

Project Presentation 1: Does Reinforcement Learning Really Incentivize Reasoning Capacity in VLMs? Slides

Project Presentation 2: Catastrophic Forgetting in Continual Learning for VLMs Across Increasing Reasoning Complexity Slides

Lecture 9:  Finetuning based VLP models

Review Paper

Paper Presentation 1: Finetuning based VLP models - Part 1 Slides

Paper Presentation 2: Finetuning based VLP models - Part 2 Slides

Project Presentation 1: Cross-Lingual Cultural Consistency: Evaluating  VLMs on African Gastronomy Slides

Project Presentation 2: Improving Low-Bit Quantization for VLA Models Slides

Lecture 10:  LLM based vision-language models

Review Paper

Paper Presentation 1: LLM based vision-language models - Part 1 Slides

Paper Presentation 2: LLM based vision-language models - Part 2 Slides

Project Presentation 1: Asymmetric Bi-Encoder for Multimodal Retrieval Slides

Project Presentation 2: Combining Generative and Discriminative Latent Representations in World Models Slides

Lecture 11: Vision-language models for modality specific tasks

Review Paper

Paper Presentation 1: Vision-language models for modality specific tasks - Part 1 Slides

Paper Presentation 2: Vision-language models for modality specific tasks - Part 2 Slides

Project Presentation 1: Adaptive Merging for Storage-Efficient Multi-Vector Visual Document Retrieval Slides

Project Presentation 2: Interpreting Visual Tokens in Video-LLMs Slides

Lecture 12: Efficient VLMs

Review Paper

Paper Presentation 1: Efficient VLMs - Part 1 Slides

Paper Presentation 2: Efficient VLMs - Part 2 Slides

Project Presentation 1: HORUS EYE - Language as Dynamic Attention for Emergency Visual Analysis Slides

Project Presentation 2: Multimodal Goal-Conditioned Humanoid Low-Level Control Slides

Lecture 13: Shortcomings of Vision-Language models

Review Paper

Paper Presentation 1: Shortcomings of Vision-Language models - Part 1 Slides

Paper Presentation 2: Shortcomings of Vision-Language models - Part 2 Slides

Project Presentation 1: Gap between generative and discriminative visual representations Slides

Project Presentation 2: Effect of Test-Time Scaling on Visual Reasoning Models Slides

Lecture 14: Beyond statistical learning in vision-language

Review Paper

Paper Presentation 1: Beyond statistical learning in vision-language - Part 1 Slides 

Project Presentation 1: Beyond Spatial QA: Cross-Viewpoint Relational Invariance in VLMs Slides

Project Presentation 2: Sketch2UML - Draw to Formalize Slides

Lecture 15: Image Generation

Review Paper

Paper Presentation 1: Image Generation - Part 1 Slides

Paper Presentation 2: Image Generation - Part 2 Slides

Project Presentation 1: Does Reinforcement Learning Really Incentivize Reasoning Capacity in VLMs? Slides

Project Presentation 2: Exploring Continual Learning on VLMs across increasing reasoning complexity to avoid Catastrophic Forgetting Slides

Lecture 16: Video understanding and generation

Review Paper

Paper Presentation 1: Video understanding and generation - Part 1 Slides

Paper Presentation 2: Video understanding and generation - Part 2 Slides

Project Presentation 1: Cross-Lingual Cultural Consistency Slides

Project Presentation 2: Improving Low-Bit Quantization for VLA Models Slides

Lecture 17: Embodied AI and World Models

Review Paper

Paper Presentation 1: Embodied AI and World Models - Part 1 Slides

Paper Presentation 2: Embodied AI and World Models - Part 2 Slides

Project Presentation 1: Asymmetric Bi-Encoder for Multimodal Retrieval Slides

Project Presentation 2: Combining Generative and Discriminative Latent Representations in World Models Slides

Lecture 18: 3D understanding and generation

Review Paper

Paper Presentation 1: 3D understanding and generation - Part 1 Slides

Paper Presentation 2: 3D understanding and generation - Part 2 Slides

Project Presentation 1: Adaptive Merging for Storage-Efficient Multi-Vector Visual Document Retrieval Slides

Project Presentation 2: Interpreting Visual Tokens in Video-LLMs Slides