Multimodal reasoning has a latency problem. More video frames leads to more waiting. We built Damage Scout with Gemma 4 on Cerebras, running at over 2,300 toks/s, to show what fast multimodal inference unlocks. Damage Scout samples frames from a rental car walkaround, sends them to Gemma 4, gets back structured findings and box coordinates, then renders an annotated damage report in under 6 seconds. Same task. Same frames. A complete different experience powered by Cerebras ⚡️

How do we ensure multimodal foundation models remain reliable when faced with real-world distribution shifts? Meet Naman Goyal and Jenny Ni today at the Google booth (#B206#) to explore how small changes like cropping, dimming, or compression can impact both a model's answers and its verification evidence. Discover why deployment reliability is tested trust, not just a clean benchmark score. #ICML2026#

Pluralis v0.1 is a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspective. Meet Lora Aroyo today at 9:30am at the Google booth (#B206#) to explore localized safety evaluation paradigms. #ICML2026#

Supporting @MITEECS and @nlp_mit’s Multimodal Machine Learning course (Spring 2026). 🎓 Students are leveraging the multimodal capabilities of Kimi K2.5 to power their final research projects. We look forward to seeing the innovative applications that will emerge this semester. 🔗 Happy coding! ✨

FLUX 3 Video from @bfl_ai is now available for everyone on OpenRouter. One unified multimodal model family for video, audio, image, and action-prediction. Serious, fun, creative, real, cinematic, whatever you need it to be. Jointly trained in one unified architecture.

Understand entire hour-long videos and wield tools and search — an efficient multimodal model with 30B total params but only 3B active at inference 🎬 Title: Kwai Keye-VL-2.0 Technical Report URL: 🎬 Overview An open-source multimodal foundation model from Kuaishou, built for long-video understanding and agentic intelligence. It's a Mixture-of-Experts (MoE) model with 30B total parameters but only 3B activated at inference. ❓ Challenges Solved Processing hour-level videos demands enormous compute. ・Many frames make long-range temporal dependencies hard to capture ・The challenge was addressing that compute constraint while keeping strong performance across diverse tasks 💡 Methodology & Proposed Approach ・Long-context: adapts DeepSeek Sparse Attention (DSA) to GQA-based architectures for lossless 256K context processing, capturing key frames and long-range temporal dependencies ・Infrastructure: scalable video I/O, heterogeneous ViT-LM parallelism, custom DSA kernels ・Training: Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) with Context-RL and Video-RL to address catastrophic forgetting during multi-task alignment 📊 Experimental Results ・State-of-the-art among models of similar scale ・Especially strong on fine-grained temporal localization (TimeLens) ・Excels at long-video comprehension on Video-MME-v2 and LongVideoBench ・Also capable at multimodal agent collaboration across Code, Tool, and Search, with self-correction 🌍 Use Cases It fits long-video understanding, search, and moderation, plus backbones for video-handling autonomous agents. As the first application of sparse attention to multimodal at this scale, its big strength is making hour-level video processing cost-realistic. #VideoUnderstanding# #Multimodal#

Integrating high-fidelity video creation, precise visual consistency, and multimodal inputs, Wan3.0 helps creators turn ideas into immersive video content. Watch the video and see creativity unleashed. ✨

Qwen3.7-Flash from @Alibaba_Qwen is live on OpenRouter. A fast vision capable reasoning model for multimodal agents, visual coding, search, and computer interaction, with tool use and a 1M context window. Try it now: