BestHub
Sign in
SmartApe AI
Author

SmartApe AI

SmartApe's AI technology content account, focusing on cutting-edge AI developments and open-source frontlines.

70
Articles
1
Likes
97
Views
0
Comments
Recent Articles

Latest from SmartApe AI

70 recent articles
SmartApe AI
SmartApe AI
Oct 24, 2026 · Artificial Intelligence

MIT Postdoc Deng Bowen Joins Fudan to Build AI Scientists for Materials Discovery

MIT postdoc Deng Bowen will join Fudan University's AI³ Institute in 2027 to lead the Atomic Intelligence Lab, aiming to build reliable AI scientists that accelerate materials discovery by integrating atomic simulation, reliability validation, and autonomous research workflows, building on his work on CHGNet, MatPES, and AtomisticSkills.

AI for materials scienceAtomisticSkillsCHGNet
0 likes · 6 min read
MIT Postdoc Deng Bowen Joins Fudan to Build AI Scientists for Materials Discovery
SmartApe AI
SmartApe AI
Oct 23, 2026 · Artificial Intelligence

Agent Cache Engineering: Tsinghua & CUHK's AKV Cuts Inference Cost 27.7% via RSI

Tsinghua and CUHK researchers introduce Cache Engineering, a paradigm where AI agents directly manage KV cache via Append, Drop, and Repos operations, avoiding re-prefill costs; their open-source AKV system achieves 27.7% inference cost reduction and 1.7% higher task scores, while recursive self-improvement with MiniMax-M2.7 discovers even better cache policies.

AI AgentsAKV SystemCUHK
0 likes · 12 min read
Agent Cache Engineering: Tsinghua & CUHK's AKV Cuts Inference Cost 27.7% via RSI
SmartApe AI
SmartApe AI
Oct 23, 2026 · Artificial Intelligence

PhysCodeGym Benchmark Catches Physics Errors in Code Agents' 4D Video Reconstruction

Shanghai Jiao Tong University and collaborators introduce PhysCodeGym, a benchmark with 156 real-video tasks requiring code agents to write executable Blender programs for 4D physical reconstruction; evaluation combines visual similarity with physical validity checks including counterfactual verification, revealing that even top models like GPT-6-Astra produce physically implausible simulations despite visual accuracy.

4D reconstructionAI evaluationBenchmark
0 likes · 18 min read
PhysCodeGym Benchmark Catches Physics Errors in Code Agents' 4D Video Reconstruction
SmartApe AI
SmartApe AI
Oct 23, 2026 · Artificial Intelligence

IQuest-Q1 Technical Deep Dive: 320B MoE Agent Model with 512K Context

IQuest Research releases technical report for IQuest-Q1, a 320B MoE model with 15B active parameters, 512K context window, recursive multi-token prediction, and agent-focused post-training, achieving strong benchmarks across coding, tool use, and reasoning tasks.

Agent TrainingBenchmark EvaluationCode Generation
0 likes · 16 min read
IQuest-Q1 Technical Deep Dive: 320B MoE Agent Model with 512K Context
SmartApe AI
SmartApe AI
Oct 22, 2026 · Artificial Intelligence

Kimi K3.1 Teased Officially; Qwen 4 Linked to Anonymous Arena Model Kalmia

Moonshot AI officially teases Kimi K3.1 with 1M token context and high thinking mode, while community tracker links anonymous Arena models Kibitz and Kalmia to Kimi and Qwen 4 respectively through tokenizer tests and 3D generation benchmarks.

3D generationAlibaba QwenAnonymous Model Testing
0 likes · 7 min read
Kimi K3.1 Teased Officially; Qwen 4 Linked to Anonymous Arena Model Kalmia
SmartApe AI
SmartApe AI
Oct 22, 2026 · Artificial Intelligence

HarnessPro: Self-Improving Agents Cut Execution Costs 26% While Raising Pass Rates

Researchers from Tsinghua, Zhipu AI, and others introduce HarnessPro, a framework where agents recursively analyze their own execution traces, identify failures and inefficiencies, and automatically rewrite their operating procedures, achieving a 2.0% pass-rate increase and 26.1% cost reduction across three benchmarks using GPT-5.5 and Codex.

AI AgentsBenchmarkCodex
0 likes · 7 min read
HarnessPro: Self-Improving Agents Cut Execution Costs 26% While Raising Pass Rates
SmartApe AI
SmartApe AI
Oct 21, 2026 · Artificial Intelligence

Recursive Open-Sources Flint-40B-A2B: AI-Designed MoE Model for Local Coding Agents

Recursive team open-sources Flint-40B-A2B, a 40B-parameter MoE model optimized for local coding agents, developed in under four months using their Eureka Machine AI research system; it achieves over 125 tokens/sec on MacBook Pro and demonstrates autonomous research capabilities on tasks like circle packing, factory scheduling (26% improvement), and bike-sharing demand prediction (30.8% RMSLE reduction).

Automated ResearchCoding AgentEureka Machine
0 likes · 6 min read
Recursive Open-Sources Flint-40B-A2B: AI-Designed MoE Model for Local Coding Agents
SmartApe AI
SmartApe AI
Oct 21, 2026 · Artificial Intelligence

Qwen-Audio-Jev: 20x Faster Audio LLM Inference via Jev Decision Heads

Alibaba's Qwen-Audio-Jev integrates Jev decision heads into an audio LLM, enabling direct classification, binary judgment, and scoring without autoregressive decoding, delivering ~20x inference speedup across 18 benchmarks including speaker verification (6.5% EER) and audio quality assessment.

Jev decision headsQwen-Audio-JevRLCD
0 likes · 14 min read
Qwen-Audio-Jev: 20x Faster Audio LLM Inference via Jev Decision Heads