We have 8 of 23 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
OPIS is introduced, an input-grounded benchmark that strictly anchors the assessment to a fixed set of object instances from the initial observation for evaluating multi-object memory in video world models and demonstrates that preserving the particular object instances in the input is considerably harder than generati...
Dr. Claw is presented, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent.
This work introduces principled criteria for desirable VQ behavior and demonstrates that aligning feature and code vector distributions provides a unifying mechanism for mitigating training instability and codebook collapse, and instantiate this framework using a Wasserstein-based objective with an efficient closed-for...
This work builds an agent harness that separates reasoning from perception and improves by evolving context rather than optimizing weights, and proposes a gradient-free, reward-gated Heuristic Skill Distillation loop that mines the agent's own low-scoring traces and keeps a candidate skill only when it raises a validat...
These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies, and provide a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable se...
WebWorld is presented, the interface that lets a VLM prior interact with this browser-as-world-model autonomously and decides which interactions become supervision and reaches the level of strong frontier systems such as Kimi-K2.6 and GPT-5.4 on interactive HTML generation.
Beyond in-domain gains, mid-training mitigates the capability erosion that agentic post-training otherwise inflicts on non-agent coding and non-coding tool-use benchmarks (tau-bench, BFCL): although the mid-training corpus contains Python code only, the function-call inductive bias survives post-training and yields con...
VGI-bench is introduced, containing 27 tasks and 810 instances, organized by a two-level taxonomy of task domains and skill tags for fine-grained evaluation of visual reasoning capabilities of video generation models, and it is hoped VGI-bench will help stimulate the development of next-generation video generation mode...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
