They also use Muon throughout the network - Router AdamW for stability - GR projections AdamW (suspected due to their weird shape) - ngram table Adam without weight decay - per head orthogornalization They trained the model with TP so for the parameter update, they come up with a parameter assigner to balance flops across ranks. The ranks then exchange via all to all

AMEC 688012: we survived earnings, always dicey w/ A -Share names. 38% top line gr (vs. LRCX 30%-->50% in Sep q) stable 40% mgns (vs LRCX 52%). News that Sammy & Hynix (China) were testing AMEC machines conveniently dropped on earnings day. Looks good thematically.

Congrats to @Alibaba_Qwen on the release of Qwen3.8-Flash-Next, using the same architecture innovations as their upcoming Qwen4 model! Such innovations include: 🟠 51-billion-param N-gram Embedding to look up a table with very little extra computation, which means the embedding table can be offloaded to slower & less expensive tiers of DRAM 🟠 Gated Residual (GR): it seems like a lot of Chinese labs are now innovating on the res connections, like Kimi's AttentionRes and DeepSeek's mHC 🟠 Qwen Sparse Attention (QSA): lightning indexer to select context at micro-block granularity Glad to see great Chinese open innovations along with end-to-end model weights to show these innovations can compose well together!

🎬 "The video looks realistic — but did it actually complete the task?" Video generation evaluation finally goes outcome-oriented. SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation 💡 Overview When generating videos that complete tasks like "cook a dish" or "prune a plant" from reference images, current models reproduce procedures reasonably well — but systematically fail to be evaluated on whether the intended end-state was actually achieved. SemComp-Bench introduces a 6-domain, 1,273-instance dataset and a dual-axis evaluation framework powered by Doubao-Seed-1.8 VLM to close this gap. ⚠️ The Problem Existing benchmarks emphasize appearance consistency and intermediate procedural steps, leaving "final outcome achievement" and "semantic grounding in reference images" unevaluated as a joint criterion. 🔬 Evaluation Framework: Two Independent Dimensions · OA (Outcome Achievement) Score: ALL four criteria must pass — outcome realization, semantic grounding, entity consistency, and global visual continuity · GR (Generation Reliability) Score: average across five failure-oriented criteria — physical plausibility, visual clarity, artifact-free rendering, spatiotemporal coherence, text integrity 📊 Results (Detailed Instruction Condition) · OA leader: HunyuanVideo-1.5-720P at 37.8% — the best model still falls short of 40% · GR leader: Seedance 2.0 at 91.8% — yet ranks 4th in OA at just 20.0% · T2V (text-only) OA: only 0.6–5.0%, confirming visual reference is indispensable · Biggest bottleneck: Within-Scene Spatiotemporal Coherence (0.328–0.739) → OA and GR are independent capabilities. Generating polished videos and completing tasks are entirely different problems. #VideoGeneration# #Benchmark#