LLMs & Foundation Models· 2026-11-10
By Mr.Xu2 views0 discussions
vLLM Overload Study Shows Cancellation Alone Cannot Stop Retry Storms
A study of overloaded vLLM deployments finds that client- and proxy-side retries can keep …
ZICQ AI News
ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleLLMs & Foundation Models
View all (3176) →LLMs & Foundation Models· 2026-11-10
By Mr.Xu1 views0 discussions
ChainFlow Cuts Speculative Decoding to One or Two Flow-Matching Steps
ChainFlow introduces a speculative-decoding drafter conditioned on the target model's hidd…
LLMs & Foundation Models· 2026-11-10
By Mr.Xu1 views0 discussions
APT Uses Aspect-wise Pairwise Voting to Improve LLM Test-Time Selection
The paper introduces Aspect-wise Pairwise Tournaments (APT), replacing absolute scoring of…
LLMs & Foundation Models· 2026-11-09
By Mr.Xu3 views0 discussions
AWS Adds Single-Shot RAG and Zero-LLM Retrieval to Bedrock Knowledge Bases
Amazon Bedrock Managed Knowledge Base now exposes three retrieval modes through the same A…
LLMs & Foundation Models· 2026-11-09
By Mr.Xu3 views0 discussions
Anthropic Launches Claude Fable and Mythos 5.2 for Coding and Long-Horizon Agents
Anthropic has released Claude Fable 5.2 and Claude Mythos 5.2, targeting difficult softwar…
Agentic
View all (2367) →Agentic· 2026-11-10
By Mr.Xu3 views0 discussions
Pass_X@k Shows Debuggers Do Not Outperform Two Bash Rollouts
The paper isolates the effect of an interactive debugger by holding the coding-agent scaff…
Agentic· 2026-11-10
By Mr.Xu1 views0 discussions
Forge Decision Context Turns Corrections into Persistent Agent Rules
Forge Decision Context (forge_dc) addresses a central limitation of LLM agents: correction…
Agentic· 2026-11-10
By Mr.Xu0 views0 discussions
NormGym Tests Social Learning: Top Agents Reach Only 55.3% Joint Success
NormGym is an interactive benchmark for normative competence in multi-agent communities. A…
Agentic· 2026-11-10
By Mr.Xu2 views0 discussions
AWS Quick Details Agent, Skill, and Data Architecture
AWS Quick organizes enterprise agents into agents, skills, spaces, and connectors. Agents …
Agentic· 2026-11-09
By Mr.Xu5 views0 discussions
AWS Unveils a Seven-Layer Pluggable Architecture for Production AI Agents
AWS has published the Pluggable Agentic AI Framework, a reference architecture for taking …
Open Source AI
View all (217) →Open Source AI· 2026-11-09
By Mr.Xu2 views0 discussions
NVIDIA Opens Nemotron-Personas-Finance-Japan Synthetic Dataset for Japan’s Financial Domain
NVIDIA has released Nemotron-Personas-Finance-Japan, a synthetic dataset designed to captu…
Open Source AI· 2026-11-07
By Mr.Xu0 views0 discussions
WorldFoundry Opens a Unified Infrastructure for Reproducible World-Model Evaluation
WorldFoundry is an open-source infrastructure for reproducible inference and evaluation ac…
Open Source AI· 2026-11-06
By Mr.Xu6 views0 discussions
NVIDIA Connects 6G Simulation, AI Training and Over-the-Air Testing with Open-Source Tools
NVIDIA's open-source AI Aerial, Sionna, and CUDA-accelerated RAN stack now connects severa…
Open Source AI· 2026-11-05
By Mr.Xu3 views0 discussions
NVIDIA Open-Sources Cosmos 3 Models for Interactive World Simulation
NVIDIA has released the Cosmos 3 open models through Hugging Face for interactive world si…
Open Source AI· 2026-11-04
By Mr.Xu3 views0 discussions
NetEase Youdao Open-Sources Confucius4-R2T2 Stable-Prefix Streaming ASR
NetEase Youdao has released and open-sourced Confucius4-R2T2, a streaming automatic speech…
Compute & Architecture
View all (74) →Compute & Architecture· 2026-11-09
By Mr.Xu4 views0 discussions
NVIDIA Releases Dynamo-Optimized Recipes for Four Korean Open Models
NVIDIA has released Dynamo-optimized deployment recipes for A.X K2, K-EXAONE 2.0, Solar Op…
Compute & Architecture· 2026-11-06
By Mr.Xu6 views0 discussions
FlexFloor Elastically Releases MoE Training Workers, Boosting RL Rollout Throughput by 52.74%
FlexFloor addresses idle worker time in reinforcement-learning post-training for mixture-o…
Compute & Architecture· 2026-11-06
By Mr.Xu9 views0 discussions
LowRAM Compresses KV Cache with Low-Rank Keys and Amortized Values
LowRAM introduces an asymmetric, post-training pipeline for compressing the KV cache used …
Compute & Architecture· 2026-11-05
By Mr.Xu3 views0 discussions
NVIDIA Vera CPU Targets Agent Execution with High Throughput and Power Efficiency
NVIDIA is positioning the Vera CPU as the execution tier for AI agents, covering informati…
Compute & Architecture· 2026-11-05
By Mr.Xu6 views0 discussions
NVIDIA Tackles the AI Memory Wall with Full-Stack Codesign
NVIDIA is addressing the memory pressure created by larger models, longer contexts, and ag…
Research & Papers
View all (1811) →Research & Papers· 2026-11-10
By Mr.Xu0 views0 discussions
Optimal Transport Reshapes Backtracking Counterfactual Inference
This paper recasts backtracking counterfactual inference in structural causal models as an…
Research & Papers· 2026-11-09
By Mr.Xu3 views0 discussions
LLM Agents for Molecular Optimization Mostly Exploit Retrieval, Not Reasoning
An ablation study of low-budget molecular optimization benchmarks finds that much of the r…
Research & Papers· 2026-11-09
By Mr.Xu2 views0 discussions
Topology-Aware Optimization Cuts ImageNet Training Time by 14.1%
IMSLab Research introduces Topological-Adaptive Optimization, including Top-SGD and Top-Ad…
Research & Papers· 2026-11-09
By Mr.Xu2 views0 discussions
AttnRes Reweights Transformer Depth per Node for Long-Range Graph Reasoning
AttnRes replaces the fixed unit-weight accumulation used in Graph Transformer residual str…
Research & Papers· 2026-11-09
By Mr.Xu2 views0 discussions
GNN-Based Generative Models Reconstruct Missing Sensor Fields for Safety-Critical Digital Twins
Researchers at Oregon State University developed a sparse-sensor reconstruction framework …
Industry & Trends
View all (637) →Industry & Trends· 2026-11-09
By Mr.Xu5 views0 discussions
OpenAI Introduces Control Room for AI Workload Governance and Rapid Shutdown
OpenAI has introduced Control Room, a centralized system for tracking model workloads acro…
Industry & Trends· 2026-11-09
By Mr.Xu5 views0 discussions
AI Data Centers Face a Power Crunch Beyond the Culture War
A field report from Virginia's Data Center Alley argues that the backlash against AI infra…
Industry & Trends· 2026-11-09
By Mr.Xu5 views0 discussions
OpenAI API Helps Kuken Industries Find Cooling Tower Drawings in Minutes
Kuken Industries is using the OpenAI API to search more than 70 years of cooling tower eng…
Industry & Trends· 2026-11-09
By Mr.Xu3 views0 discussions
Disney and Adobe Build Proprietary Artist-Led Generative AI Tools
Disney and Adobe have announced a multi-year strategic alliance to develop proprietary “ar…
Industry & Trends· 2026-11-09
By Mr.Xu4 views0 discussions
RIAA Pushes AI-Music Labels and Licensing Rules as Deepfakes Intensify
In a The Verge interview, RIAA CEO Mitch Glazier called for interoperable, machine-readabl…
大语言模型
大语言模型· 2026-10-09
By Mr.Xu9 views0 discussions
Hugging Face Releases PreSTO: A New Method for Accelerating LLM Inference
Hugging Face has introduced PreSTO, a novel method for accelerating the inference process …
Safety & Privacy
Safety & Privacy· 2026-08-10
By Mr.Xu13 views0 discussions
Checkpoint Research Exposes Potential Security Risks in Cloudflare Code Mode and Workers
Checkpoint Research has published a study on Cloudflare's Code Mode and Workers, highlight…