LLMs & Foundation Models· 2026-11-05
By Mr.Xu0 views0 discussions
HuggingBench Audit Exposes Identity Mismatches and Training-Budget Biases
The authors audit HuggingBench as a versioned data product rather than treating a benchmar…
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 (3133) →LLMs & Foundation Models· 2026-11-05
By Mr.Xu0 views0 discussions
Long-Horizon Federated Learning Exposes Trust-Boundary Drift; Held-Out Audits Preserve 98% of Gains
A long-horizon benchmark for receiver-directed federated learning tracks how each site adm…
LLMs & Foundation Models· 2026-11-05
By Mr.Xu0 views0 discussions
RAGCompass Routes Retrievers by Evidence, Generalizing to Unseen Corpora
RAGCompass addresses a central limitation of multi-retriever RAG systems: no single retrie…
LLMs & Foundation Models· 2026-11-05
By Mr.Xu0 views0 discussions
BACE Calibrates When LLMs Should Ask Before Committing to an Answer
This paper addresses the tendency of large language models to answer ambiguous referring e…
LLMs & Foundation Models· 2026-11-05
By Mr.Xu1 views0 discussions
DS@GT ARC Generates Fact-Checking Articles with a Verdict-Anchored Pipeline
DS@GT ARC has developed a four-stage pipeline for CLEF 2026 CheckThat! Lab Task 3. It clea…
Agentic
View all (2324) →Agentic· 2026-11-05
By Mr.Xu0 views0 discussions
SlackBench Benchmarks Collaborative Agents Across Code and Workplace Conversations
SlackBench introduces a reproducible environment for evaluating agents on collaborative re…
Agentic· 2026-11-05
By Mr.Xu0 views0 discussions
ReScopeBench Evaluates the Experience Lifecycle of Long-Lived Agents
ReScopeBench evaluates how long-lived agents acquire, reuse, revise, and lose experience a…
Agentic· 2026-11-05
By Mr.Xu1 views0 discussions
Challenger-Guided Adaptive Recruitment for Medical Multi-Agent Reasoning
A medical multi-agent study replaces question-time retrieval with adaptive intervention dr…
Agentic· 2026-11-05
By Mr.Xu1 views0 discussions
CRO Reserves Compute and Bandwidth for AI Agents with Conformal Prediction
This arXiv paper introduces Conformal Reservation for Orchestration (CRO), an online sched…
Agentic· 2026-11-05
By Mr.Xu1 views0 discussions
Agent Harness Awareness Gives Tool-Using Agents Verified Runtime State Before Dispatch
The paper introduces Agent Harness Awareness, a trust-separated architecture in which the …
Open Source AI
View all (212) →Open Source AI· 2026-10-28
By Mr.Xu4 views0 discussions
Akai Embraces Open Source with MPC Sample Key, Inviting Community Modding
Akai is set to release the MPC Sample Key, an open-source hardware device aimed at music c…
Open Source AI· 2026-10-28
By Mr.Xu4 views0 discussions
Hugging Face Open-Sources Skill Dreaming: Optimizing Repository Skills via Pull Request Streams
Hugging Face has introduced the Skill Dreaming framework, designed to optimize repository-…
Open Source AI· 2026-10-27
By Mr.Xu2 views0 discussions
LangChain Open-Sources Content Studio: AI-Powered Design Agent for Branded Content Creation in Slack
LangChain has open-sourced Content Studio, an AI-powered design agent integrated into Slac…
Open Source AI· 2026-10-26
By Mr.Xu3 views0 discussions
Hugging Face Releases Lipi-Ghor: The First Large-Scale Annotated Bengali Speech Corpus
Hugging Face has released Lipi-Ghor, the first large-scale Bengali speech corpus featuring…
Open Source AI· 2026-10-25
By Mr.Xu3 views0 discussions
Hugging Face Releases QuantCheck Tool: Detecting Non-Functional Quantized LLMs in Public Registries
Hugging Face has released an open-source tool called QuantCheck to detect non-functional q…
Compute & Architecture
View all (66) →Compute & Architecture· 2026-11-05
By Mr.Xu1 views0 discussions
When Is Tiered LLM Inference Worth It? A Cost-Structure Boundary
A theoretical analysis models confidence-gated tiered inference as a binary routing decisi…
Compute & Architecture· 2026-11-04
By Mr.Xu1 views0 discussions
Together AI Introduces Polymorphic Inference for Continuously Tuned Production Serving
Together AI has introduced Polymorphic Inference together with Together Compiler, using AI…
Compute & Architecture· 2026-11-04
By Mr.Xu1 views0 discussions
Qualcomm Bets on AI Data Centers as Smartphone Sales Decline
Qualcomm sharply raised its AI data-center outlook during its FY2026 Q4 earnings call. The…
Compute & Architecture· 2026-10-30
By Mr.Xu4 views0 discussions
Google's First Data Center Satellite Online: Running Gemma 4 and Writing Poetry
Google has announced the online deployment of its first data center satellite, which runs …
Compute & Architecture· 2026-10-29
By Mr.Xu6 views0 discussions
AWS Launches Batch Quota Management to Optimize SageMaker Training Resource Allocation
AWS has introduced a new quota management capability for AWS Batch, enabling administrator…
Research & Papers
View all (1742) →Research & Papers· 2026-11-05
By Mr.Xu0 views0 discussions
SSPE Reconstructs Staypoints Under Spatial Noise and Signal Dropouts
The paper introduces Sequential Staypoint Extraction (SSPE), a state-driven method for rec…
Research & Papers· 2026-11-05
By Mr.Xu1 views0 discussions
MIS Brings Prefix-Aware Whole-Page Ranking with One-Pass Inference
The paper introduces Multi-Item Scoring (MIS), a prefix-aware, non-autoregressive framewor…
Research & Papers· 2026-11-05
By Mr.Xu0 views0 discussions
Minimal Superior Penalties Redefine Model-Selection Metrics—and Expose an Attribution Gap
This work examines whether a validation metric used for checkpoint selection and early sto…
Research & Papers· 2026-11-05
By Mr.Xu0 views0 discussions
MA-SafeDiffuser Extends Diffusion Planning to Multi-Agent Safety
MA-SafeDiffuser extends SafeDiffuser’s control-barrier-function (CBF) constraints to diffu…
Research & Papers· 2026-11-05
By Mr.Xu0 views0 discussions
Finsler-Randers Metric Learning Adds Directionality to Latent-Space Exploration
This paper introduces a Finsler-Randers metric-learning framework for latent spaces, where…
Industry & Trends
View all (625) →Industry & Trends· 2026-11-05
By Mr.Xu0 views0 discussions
Big Tech's $720B AI Infrastructure Bet Shows No Signs of Cooling
Amazon, Microsoft, Alphabet, and Meta have indicated that their combined 2026 capital expe…
Industry & Trends· 2026-11-04
By Mr.Xu0 views0 discussions
US Midterm Elections Tighten the Path to Data Center Expansion
The 2026 US midterm elections are reshaping the approval environment for data center devel…
Industry & Trends· 2026-11-04
By Mr.Xu2 views0 discussions
Google’s AI Search Traffic Grows Faster Than Its Monetization
Alphabet reported that Google Search queries grew at their fastest rate in five years, yet…
Industry & Trends· 2026-11-04
By Mr.Xu1 views0 discussions
Texas Political Shift Threatens the AI Data Center Buildout
Texas is moving from an incentive-first approach toward tighter oversight of data center d…
Industry & Trends· 2026-11-03
By Mr.Xu1 views0 discussions
Google Disables Search in Schools Rejecting AI Features
Google has announced that it will completely disable its search services in schools that r…
大语言模型
大语言模型· 2026-10-09
By Mr.Xu6 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.Xu11 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…