10 papers · 1 filter
Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
Shravan Venkatraman, Omkar Thawakar, Ritesh Thawkar +2
Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alt…
Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards
Ritesh Thawkar, Shravan Venkatraman, Omkar Thawakar +5
Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations,…
Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar +4
Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and se…
EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards
Omkar Thawakar, Shravan Venkatraman, Ritesh Thawkar +5
Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated dat…
Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
Abdelrahman Shaker, Ahmed Heakl, Jaseel Muhammad +8
Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on…
How Good are Foundation Models in Step-by-Step Embodied Reasoning?
Dinura Dissanayake, Ahmed Heakl, Omkar Thawakar +9
Embodied agents operating in the physical world must make decisions that are not only effective but also safe, spatially coherent, and grounded in context. While recent advances in…