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.

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition Sage-A1.5 composes delegation, parallel subagents, verification, and strategy revision for long-horizon problem solving.

Calibrated Typed Decisions for Entity, Relation, and Event Extraction CalOn unifies entity, relation, and event extraction in a 0.6B-parameter encoder that jointly reads text and type definitions.

SolarRenderer: Few-Step Generative Reference Rendering SolarRenderer adapts a frozen video backbone with two LoRAs, injecting frame-aligned structural videos through its native reference pathway for representation-agnostic control.