📢 World Premiere Listing: QAIT @Sealcoin_QAIT $QAIT Is Coming to #KuCoin#! The QAIT Association is a Swiss non-profit organization dedicated to advancing trusted, decentralized digital infrastructure and enabling autonomous machine economies. 📅 Trading Starts: 13:00 on May 28, 2026 (UTC) 💰 Deposits: Will open at 04:00 on May 28, 2026 (UTC) (BSC-BEP20) 🔁 Pair: QAIT/USDT Details: #KuListing# #QAIT#

👀 Top Crypto Fundraising Last Week 1️⃣ Kiavi (@kiavi_inc) - $717.0M; Real Estate 2️⃣ Canton Network (@CantonNetwork) - $335.0M; Privacy, Smart Contract Platform 3️⃣ Morpho (@morpho) - $175.0M; Lending, DAO 4️⃣ Edge Markets (@edge_marketsio) - $29.0M; 5️⃣ Vinyl Equity (@vinylequity) - $20.0M; 6️⃣ Siiibo Securities (@siiibo) - $13.0M; 7️⃣ Ai Pay With Crypto (@aipaywithcrypto) - $10.0M; API, AI Agents 8️⃣ MNX (@MNX_fi) - $6.4M; DEX, Perpetuals 9️⃣ TVL Capital (@TVLCap) - $5.0M; 🔟 SEALCOIN (@Sealcoin_QAIT) - $4.0M; Internet of Things (IoT)

My agent is making me a custom Voice Assistant app for my Pixel Watch so I can send recordings directly to my agents. The /pr skill is SO NICE for capturing visual changes without needing to QA it. I love AI

AI agents watching video don't need long-form generation, they need fast judgments. VideoJev pushes that idea to its logical extreme. Title: VideoJev: System One Model for Video Understanding and Interaction URL: It unifies temporal grounding (finding the right video segment) and video question-answering under one design: scoring candidates directly. Here are three things worth knowing. 🎯 Scoring instead of generating The output head of a pretrained MLLM is replaced with a candidate scorer, so instead of generating tokens one by one, the model directly scores time intervals and text options. Trained on identical data, this approach beats autoregressive fine-tuning by 1.3 points on grounding and 1.9 points on QA. ⚡ Two inference modes for smart speedups Cached inference encodes the video once, while Joint inference processes multiple queries together in a single forward pass. Even at ten queries per video, the added cost is just tens of milliseconds, and prediction quality actually improves. 📈 Speed and accuracy, both at once On temporal grounding it improves mIoU by up to 10.8 points while running 2.8-3.1x faster, and on video QA it matches accuracy while delivering over 100x speedups. Judging instantly rather than "thinking then answering" looks like a real step forward for making visual agents responsive in real time. #VideoAI# #AIAgents#

For long-context LLM inference, should the KV cache be offloaded to disk or just recomputed on the GPU? There's no universal right answer, and this paper builds a system that decides quantitatively. Title: Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs URL: 📝 Overview The paper proposes py-kvcache, an external KV cache system for vLLM. Using io_uring for async I/O, even a Python implementation pulls near-full SSD read bandwidth of 13.5GB/s. ❗ Problem it solves Existing external KV caches like LMCache have no criteria for when to actually use them — they load from disk unconditionally even when a short prefix or a fast GPU makes recomputation cheaper. ⚙️ Methodology It introduces "scheduler-aware preloading," which starts disk reads while a request is still waiting to be scheduled, plus a "break-even gate" that rejects a load whenever it wouldn't improve time-to-first-token. 📊 Results On LongBench multi-document QA it's 6.02-7.43x faster than GPU recomputation and 2.77-3.64x faster than LMCache. On multi-turn SCBench, native vLLM read 3.4TB from disk with completion times over 1200s, while py-kvcache kept disk reads to 85GB and completion time to 480s. 🖥️ Use cases On a high-end H100, requests often don't even clear the break-even point, so skipping external caching is fine — but on a lower-end RTX 4000 Ada, external caching clearly wins, giving concrete hardware-specific guidance. #LLMInference# #vLLM#