…Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation (2026) RLDX-1 Technical Report (2026) VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis (2026) PhyWorld: Physics-Faithful World…
…Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026) OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation (2026) Please give a thumbs up to this comment…
…unified framework that recommends models in real-world scenarios by learning from public leaderboard data to rank unseen models on unseen datasets without requiring costly evaluations. AI-generated summary The open-source…
…While specialized Time Series Foundation Models (TSFMs) excel at forecasting based on numerical patterns, they remain unaware to real-world textual signals. Conversely, while LLMs are emerging as zero-shot forecasters, their…
…In addition, we extend existing quantitative evaluation metrics by proposing a new image-based similarity evaluation framework that assesses image fidelity and identity preservation through comparisons between real-world reference images and…
…We introduce BraveGuard, a self-evolving defense framework for training guard models from open-world threat signals and realistic agent trajectories . BraveGuard mines recent research sources to identify emerging risks and attack…
…From Vision-Language-Action Models to a Real-World Robot Learning Stack Published on Jun 12 Submitted by taesiri on Jun 15 Tencent Hunyuan Authors: , , , , , , , , , , , , , , , , , , , , , Abstract HyVLA-0.5 is an end…
…A Unified Multimodal Agent for World-Grounded Image Synthesis (2026) Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges (2026) From Visual Synthesis to Interactive Worlds: Toward…
…Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier VLAs (e.g. π_{0.5} and GR00T N1.6) across both simulation benchmarks and real-world tasks that require…
…Benchmarking Web Agents on Realistic Long Horizon Tasks (2026) Beyond Binary Correctness: Scaling Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks (2026) SWE-Next: Scalable Real-World Software Engineering Tasks for…