We have 8 of 27 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.
Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response reuse. Token-wise importance weighting avoids multiplying likelihood ratios across a response but generally biases policy gradients. We prove that, under coverage and...
Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and...
LLM-based agents are increasingly capable of generating complex 3D structures, with the potential to reshape how objects are designed and realized in the physical world. Yet, producing elegant geometry is fundamentally different from producing objects that can be built and perform their intended functions. Existing eva...
MotorMind is introduced, a robot manipulation harness that connects VLM-proposed mid-level actions to deterministic robot control and feedback, with asynchronous monitoring and background memory updates, and shows that a general-purpose VLM, when equipped with an appropriate mid-level action representation and asynchro...
MiCRo is introduced, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations and effectively captures diverse human preferences and significantly improves downstream personalization.
A single algorithm attains the instance-wise lower bound up to an additive two-arm term of Chen and Li's gap-entropy and almost instance-wise optimality conjectures in the best-arm identification problem.
The predictive divergence mask is proposed, which asks whether the next policy-gradient step will increase or decrease the same divergence used by the trust region, and the resulting masks improve RL training across model scales and precision settings.
This work presents SceneActBench, a benchmark for visually conditioned action across five 3D tasks under a unified agent-environment loop, and evaluates each final output against hidden ground truth with task-specific geometric metrics.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
