BestHub
Sign in
Tagged articles

fast weights

3 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 22, 2026 · Artificial Intelligence

Tsinghua’s Spatial‑TTT Beats Gemini: Continuous Spatial Intelligence Wins ECCV 2026

Spatial‑TTT, a 2‑billion‑parameter open‑source multimodal model, uses fast‑weight updates, a hybrid TTT architecture, a spatial‑predictive mechanism and dense 3D scene supervision to maintain and refresh a spatial memory while processing up to 120‑minute video streams, outperforming Gemini‑3‑pro and other closed‑source baselines on multiple spatial‑intelligence benchmarks with over 40% lower memory and compute cost.

ECCV2026Spatial-TTTfast weights
0 likes · 13 min read
Tsinghua’s Spatial‑TTT Beats Gemini: Continuous Spatial Intelligence Wins ECCV 2026
Machine Heart
Machine Heart
Jun 5, 2026 · Artificial Intelligence

Do LLMs Need Sleep? CMU Paper Shows Memory Consolidation Improves Reasoning

Researchers from CMU and collaborators propose a ‘sleep’ phase for transformer‑based LLMs that repeatedly re‑processes accumulated context to update fast weights in a state‑space module, enabling memory consolidation that reduces KV‑cache pressure and markedly improves performance on long‑context, multi‑step reasoning benchmarks.

LLMSSMfast weights
0 likes · 10 min read
Do LLMs Need Sleep? CMU Paper Shows Memory Consolidation Improves Reasoning
21CTO
21CTO
Jun 2, 2024 · Artificial Intelligence

Geoff Hinton on Scaling Laws, Multimodal AI, and the Future of Intelligence

In a candid interview, Geoff Hinton reflects on his AI journey—from early disappointments in physiology and philosophy to breakthroughs in neural networks, scaling laws, multimodal learning, fast‑weight concepts, and the ethical challenges shaping the future of artificial intelligence.

AI ethicsDeep LearningGeoff Hinton
0 likes · 25 min read
Geoff Hinton on Scaling Laws, Multimodal AI, and the Future of Intelligence