…fdefinedeeemodeThe code is available at https://github.com/intcomp/Sub-JEPA. View arXiv page View PDF Project page GitHub 34 Add to collection Community We introduce Sub-JEPA, a simple improvement over…
…training speed and optimization performance. Code at https://github.com/millioniron/ROLL. View arXiv page View PDF GitHub 3 Add to collection Community Asynchronous reinforcement learning improves rollout throughput for large language…
…Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC…
…When integrated into the AnalogCoder agentic framework as a retrieval-augmented generation module, it consistently improves functional pass rates and enables previously unsolved tasks to be completed. Our code and dataset will…
…a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module…
…First, post-training a base generator with FD-loss in different representation space s consistently improves visual quality. Under the Inception feature space , a one-step generator achieves0.72 FID on ImageNet…
…AI-generated summary Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity , which measures pixel-level faithfulness…
…We then perform Tool-Bootstrapped GUI RFT , combining warmup SFT with single-turn RL to improve decisions at critical GUI-Tool switching points. Finally, we optimize ToolCUA with Online Agentic RL in…
…Second, iterative refinement improves correctness , but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from 1.58times to 1.44times; newly rescued…
…As these models scale to larger backbones and higher-resolution inputs, improving their efficiency becomes increasingly important for practical deployment. However, modern 3D transformer pipelines face two coupled challenges: dense multi-view…