Has GPT-6-Astra Achieved Embodied Intelligence?
Paper • 2610.22471 • Published • 422
Abdelfatah Aldonza
abdelfataha
AI & ML interests
Agent systems for real-world tasks. Building practical tools.
Recent Activity
upvoted a paper 1 day ago
Has GPT-6-Astra Achieved Embodied Intelligence? upvoted a paper 1 day ago
Lexical Reference Frames: Interpreting LM Residual Streams in Native SemanticsOrganizations
None yet
upvoted 20
papers 1 day ago
Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics
Paper • 2610.22169 • Published • 48
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement
Paper • 2607.18217 • Published • 64
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Paper • 2606.08671 • Published • 44
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Paper • 2608.13558 • Published • 94
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Paper • 2607.16617 • Published • 143
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Paper • 2608.25593 • Published • 115
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
Paper • 2605.23271 • Published • 75
OpenRath: Session-Centered Runtime State for Agent Systems
Paper • 2606.19409 • Published • 76
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Paper • 2607.06559 • Published • 92
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Paper • 2606.09426 • Published • 109
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
Paper • 2607.25895 • Published • 157
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Paper • 2607.27205 • Published • 135
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs
Paper • 2608.01755 • Published • 139
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 168
Kwai Keye-VL-2.0 Technical Report
Paper • 2606.10651 • Published • 193
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting
Paper • 2607.28261 • Published • 114
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 149
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Paper • 2606.11324 • Published • 166
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 207