FlashMap drafts 16 tokens in a single pass and hits up to 6.14x lossless decoding speedup on Qwen3-8B. It's a speculative decoding drafter built on flow maps, from Polymathic AI, Princeton and USC ISI researchers. Instead of drafting token by token, it drafts the whole block jointly, and the target model still verifies it, so output quality doesn't change. #LLM #AI

Liquid AI's LFM3 family is 6 open-weight 2B-class models covering text, vision, audio, omni and decisions. LFM3-1.7B runs a tri-hybrid backbone with a 256K context window, and it fits in about 1 GB at 4-bit. That's long-context multimodal on a phone-sized memory budget. #AI #OpenWeights #LLM

Frontier AI agents build the training worlds, replay real-world motion, and tune physics for Agile’s ONE SN humanoid before it ever moves. The 88-pound, 31-degree-of-freedom robot is built on NVIDIA Isaac GR00T and powered by Jetson Thor. #humanoid #NVIDIA

Baidu's Unlimited-OCR-2 parses documents of any length with near-constant decoding latency and memory. The trick is Sparse Reference Sliding Window Attention (SR-SWA). It squeezes text-visual attention down to a fixed working set (e.g. 512 tokens), so per-step cost doesn't grow with page count. It claims SOTA on both MPDocBench (dozens of pages) and MarathonDocBench (hundred-page docs). #AI #OCR

OpenAI's GPT-6.1 Terra matches GPT-6 Astra's medium-effort score on Agents' Last Exam at $0.29 per task, versus $4.82 for Astra. It's a fast computer-use and vision model priced at $1/$5 per million tokens, which halves GPT-6.1 Sol's API price for agent work. Agent workloads just got far cheaper to run at scale. #AI #LLM

Stanford and UC Berkeley just dropped TokenGate: a drop-in learned token pruning module that cuts long-context prefill time-to-first-token by 1.4x to 11.3x. Peak memory falls 1.5x to 3.4x, with no accuracy loss. Token-gated attention decides which tokens are worth attending to before the expensive part runs, so long prompts stop eating your latency budget. #AI #LLM

Nanbeige4.3-33B scores 80.9 on Terminal-Bench 2.1, and it's a 33B dense model under Apache 2.0. Built for agentic coding, with 512K context. It will also serve as the teacher for the upcoming Nanbeige4.3-3B, so a small distilled version is on the way. Open weights at this size aimed squarely at terminal agents is worth watching. #AI #LLM #OpenSource

Cerebras has published how it deploys trillion-parameter frontier models on its hardware. Wafer-scale chips were built for small and mid-size models. Serving 1T+ parameter models on them is a different engineering problem, and the write-up covers how Cerebras handles it. Worth a read if you follow inference infrastructure beyond GPU clusters. #AI #LLM

A 763B-parameter MoE with 1M context, quantized to 2.00 bits per weight, matches the base model on every benchmark tested. It runs on a single 12 GB GPU. ISTA's GSQ + RCO GGUFs of DeepSeek-V4.1-Flash-1017 at IQ2_XXS (reasoning effort 50): AIME25 100.00, GPQA-Diamond 90.91, LiveCodeBench v6 89.71, all identical to base. The 110.6 GB Engram tables are read one row per token, so they stay memory-mapped on disk. llama.cpp doesn't support V4.1 yet, so the GGUFs run in Strata for now. #LLM #Quantization

NVIDIA just released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B that targets about 4GB of VRAM. It's built for local voice assistants, game characters and robots, and it runs on RTX GPUs and Jetson. That puts a capable on-device agent brain on consumer and edge hardware, with no cloud round trip. #AI #LLM #OpenSource