-
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Paper • 2605.15182 • Published • 38 -
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 42 -
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Paper • 2605.14392 • Published • 7 -
World Action Models: The Next Frontier in Embodied AI
Paper • 2605.12090 • Published • 64
Madalin Tatarciuc
cetusian
AI & ML interests
instinctively gravitating toward the frontier where intelligence meets constraints.
Recent Activity
upvoted an article about 7 hours ago
OlmoEarth v1.1: A more efficient family of models liked a model 1 day ago
hotchpotch/query-crafter-japanese-Qwen3-1.7B liked a model 1 day ago
nvidia/canary-qwen-2.5bOrganizations
