AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 115
Kye Gomez
kye
AI & ML interests
Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,
Recent Activity
upvoted a paper about 3 hours ago
AREX: Towards a Recursively Self-Improving Agent for Deep Research upvoted a paper about 3 hours ago
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers upvoted a paper about 3 hours ago
LLMs Get Lost in Evolving User IntentOrganizations
upvoted 3
papers about 3 hours ago
upvoted 4
papers 2 days ago
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Paper • 2607.18754 • Published • 23
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
Paper • 2607.18367 • Published • 52
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Paper • 2607.19064 • Published • 62
Generative World Renderer at the Speed of Play
Paper • 2607.18703 • Published • 72
upvoted 7
papers 3 days ago
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Paper • 2607.17972 • Published • 6
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
Paper • 2607.16074 • Published • 8
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 164
Group Entropy-Controlled Policy Optimization
Paper • 2607.16850 • Published • 29
FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
Paper • 2607.18171 • Published • 6
GigaChat Audio: Time-aware Large Audio Language Model
Paper • 2607.10387 • Published • 36
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Paper • 2607.17977 • Published • 195
upvoted 5
papers 7 days ago
DeepLoop: Depth Scaling for Looped Transformers
Paper • 2607.13491 • Published • 16
From Pixels to States: Rethinking Interactive World Models as Game Engines
Paper • 2607.14076 • Published • 35
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 197
BadWAM: When World-Action Models Dream Right but Act Wrong
Paper • 2607.15207 • Published • 53
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 168
upvoted a paper 8 days ago