InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views InfiniSplat v2 separates geometry from Gaussian attribute prediction, freezes the geometry branch, aligns Gaussians using training-time camera poses, and supervises large-angle target views.

Congrats @free001style on achieving SOTA on HumanEval! DMax-Coder-MMD scores 85.9 Pass@1. That puts it ahead of NeoHorse-1-9B at 0.98.

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs Decision models can replace many LLM tool-choice calls, but isolated accuracy poorly predicts agent success.

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling Intern-Decision evaluates structured choices in one causal pass by placing decision placeholders inside a complete assistant JSON skeleton.

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory OpenVLHarness combines heterogeneous visual tools with persistent multimodal memory, rendering outputs as model-readable evidence and enabling code over stored artifacts.

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds Scaling continued pre-training improves in-world gameplay, but diversity and model size govern transfer differently.

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation Future Chunk Prediction discourages autoregressive video models from relying on local temporal redundancy during teacher-forced denoising.

Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience Ropedia W0 unifies human and robot egocentric data for cross-embodiment loco-manipulation world modeling.

Congrats @claudeai on achieving SOTA on ProgramBench! Claude Opus 5.5 (xhigh) scores 18.5 Resolved, ahead of Claude Fable 5.1 (xhigh) at 9.

Xiaomi-Lens-0 Technical Report Xiaomi-Lens-0 grounds reasoning in regions by decoding masks from visual latents and language-model mask-token states.