Thinking with Visual Grounding
Paper • 2606.16122 • Published • 10
Kye Gomez
kye
AI & ML interests
Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,
Recent Activity
upvoted a paper 3 days ago
Thinking with Visual Grounding upvoted a paper 3 days ago
Context-Aware RL for Agentic and Multimodal LLMs upvoted a paper 3 days ago
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM PipelinesOrganizations
upvoted 5
papers 3 days ago
Context-Aware RL for Agentic and Multimodal LLMs
Paper • 2606.17053 • Published • 11
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
Paper • 2606.19605 • Published • 10
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents
Paper • 2606.19704 • Published • 30
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Paper • 2606.20515 • Published • 38
upvoted 6
papers 4 days ago
ViT-Up: Faithful Feature Upsampling for Vision Transformers
Paper • 2606.14024 • Published • 8
CEO-Bench: Can Agents Play the Long Game?
Paper • 2606.18543 • Published • 8
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
Paper • 2606.15872 • Published • 8
Native Active Perception as Reasoning for Omni-Modal Understanding
Paper • 2606.19341 • Published • 16
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Paper • 2606.17682 • Published • 25
Kairos: A Native World Model Stack for Physical AI
Paper • 2606.16533 • Published • 36
upvoted 9
papers 5 days ago
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Paper • 2606.18023 • Published • 200
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
Paper • 2606.17730 • Published • 8
Rethinking the Role of Efficient Attention in Hybrid Architectures
Paper • 2606.15378 • Published • 16
MotionVLA: Vision-Language-Action Model for Humanoid Motion
Paper • 2606.15142 • Published • 3
RepSelect: Robust LLM Unlearning via Representation Selectivity
Paper • 2606.17168 • Published • 4
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
Paper • 2606.15231 • Published • 4
Variable-Width Transformers
Paper • 2606.18246 • Published • 12
Looped World Models
Paper • 2606.18208 • Published • 453
Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
Paper • 2606.18249 • Published • 14