Tracked topic
…Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions, leaving us unable to localize failures to writing, maintenance, retrieval…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Language models (LMs) represent tokens using embedding matrices that scale linearly with the vocabulary size . To constrain the parameter footprint, prior work proposes hashing…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science. However…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation , repository-level coding, and agentic workflows whose accumulated reasoning and…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Predicting object dynamics (i.e., world modeling ) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due…
…Qwen/Qwen2.5-Coder-32B-Instruct Advances in radiance fields have enabled photorealistic novel view synthesis . In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and…
…for localized refinement, such as adjusting a jump trajectory or adding an interaction, with minimal disruption to the global scene context. Extensive evaluations on the nuScenes , HO-3D , and BEHAVE benchmarks demonstrate…