LLMs & Foundation Models· 2026-11-13
By Mr.Xu1 views0 discussions
Proof-Step Verification Raises Precision but Sacrifices Coverage
This study evaluates a proof-step verification pipeline that rewrites model-generated math…
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 (3229) →LLMs & Foundation Models· 2026-11-13
By Mr.Xu1 views0 discussions
Jev Evaluated as a Multilingual Judge: Accuracy at One-Thirtieth of GPT-6.1 Cost
Researchers evaluated Jev against a generative LLM judge on four human-annotated multiling…
LLMs & Foundation Models· 2026-11-13
By Mr.Xu0 views0 discussions
FairSumEval Separates Evidence Omissions from Unsupported Agreement in Discharge Summaries
FairSumEval introduces an evidence-aware, fact-level evaluation framework for clinical dis…
LLMs & Foundation Models· 2026-11-13
By Mr.Xu1 views0 discussions
MDU Benchmark Exposes Multilingual Document-Understanding Gaps That Scale Does Not Close
MDU is a multilingual document-understanding benchmark covering 13 tasks, five languages, …
LLMs & Foundation Models· 2026-11-13
By Mr.Xu1 views0 discussions
MITRA-Swarm Decomposes Classical Sanskrit Translation with Explicit Linguistic Structure
MITRA-Swarm decomposes classical Sanskrit machine translation into explicit Sandhi segment…
Agentic
View all (2425) →Agentic· 2026-11-13
By Mr.Xu1 views0 discussions
PRaVaSS Preserves Uncertain State Beliefs for More Robust Vision-Language Agent Planning
Vision-language agents commonly collapse uncertain perception outputs into one best-guess …
Agentic· 2026-11-13
By Mr.Xu1 views0 discussions
Simulate What-If Users Before Shipping With Persona-Based Agent Experiments
This work presents a framework for persona-based user simulation that formalizes target co…
Agentic· 2026-11-13
By Mr.Xu0 views0 discussions
Time Is the Signal: Humans Outperform AI at Adaptive Social Coordination
Researchers evaluated 150 human participants, computer-use agents, and text-prompted langu…
Agentic· 2026-11-13
By Mr.Xu2 views0 discussions
SynthCorp Generates Enterprise Data-Agent Benchmarks Through Traceable Event Simulation
SynthCorp creates customizable data estates and benchmarks for LLM-driven data agents by s…
Agentic· 2026-11-13
By Mr.Xu1 views0 discussions
Cleaning Agent History Can Backfire When the World Still Contains the Error
This study separates an agent's conversational history from the state of the external worl…
Open Source AI
View all (221) →Open Source AI· 2026-11-13
By Mr.Xu0 views0 discussions
KernelMosaic Open-Sources CUDA Kernel Dataset and Training Trajectories
KernelMosaic introduces an open dataset and agentic framework for training models to gener…
Open Source AI· 2026-11-11
By Mr.Xu3 views0 discussions
AWS Opens 23 Production-Ready Generative AI Assets for Faster RAG and Agent Delivery
AWS has consolidated 23 production-oriented generative AI building blocks from the AWS Gen…
Open Source AI· 2026-11-10
By Mr.Xu1 views0 discussions
TorchCurves Open-Sources Differentiable Parametric Curves for PyTorch
TorchCurves packages B-spline and Legendre-polynomial parametric curves as learnable PyTor…
Open Source AI· 2026-11-10
By Mr.Xu5 views0 discussions
MiniMax Open-Sources H3-Image for 10-Second 4K Image Generation
MiniMax has released H3-Image, an open-weight image generation model built on H3. It suppo…
Open Source AI· 2026-11-09
By Mr.Xu6 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…
Compute & Architecture
View all (82) →Compute & Architecture· 2026-11-13
By Mr.Xu1 views0 discussions
Together Compiler Uses a Continual Agent Loop to Accelerate AI Inference
Together AI has introduced Together Compiler (TKCC), a continual compilation system for pr…
Compute & Architecture· 2026-11-12
By Mr.Xu2 views0 discussions
SGLang-Neuron Brings Native PyTorch Inference to AWS Trainium
AWS, RadixArk, and Annapurna Labs have released SGLang-Neuron through an AWS Deep Learning…
Compute & Architecture· 2026-11-10
By Mr.Xu1 views0 discussions
FAME-QP Accelerates Real-Time Model Predictive Control with Fused CUDA Kernels
FAME-QP is a GPU-accelerated solver for dense quadratic programs generated by linear model…
Compute & Architecture· 2026-11-10
By Mr.Xu3 views0 discussions
Google Adds Two Specialized TPUs for Confidential Training and Larger Memory Workloads
Google is expanding its Tensor Processing Unit portfolio with two specialized chips aimed …
Compute & Architecture· 2026-11-10
By Mr.Xu4 views0 discussions
LoRazor Trims LoRA Adapter Execution to Triple Multi-LoRA Throughput
LoRazor is a multi-LoRA serving framework designed for shared-backbone deployments. It all…
Research & Papers
View all (1935) →Research & Papers· 2026-11-13
By Mr.Xu0 views0 discussions
GenPFN Uses a Frozen TabPFN to Generate Engineering Candidates and Cut Regression Error by 62.1%
GenPFN introduces a training-free candidate generator for data-scarce engineering design. …
Research & Papers· 2026-11-13
By Mr.Xu1 views0 discussions
LLMs Homogenize Teaching: Diversity Prompts Do Not Broaden Instruction
A study of math-item generation and essay feedback finds that outputs from frontier and op…
Research & Papers· 2026-11-13
By Mr.Xu0 views0 discussions
Disentangling Tokenizer Gains: Real Root Assignment Helps Amharic NER
This study separates three effects commonly conflated in tokenizer comparisons: tokenizati…
Research & Papers· 2026-11-13
By Mr.Xu1 views0 discussions
Distributionally Robust BEST-RQ Improves Speech Representations Across Codebooks
BEST-RQ learns efficient speech representations from large-scale unlabeled audio through r…
Research & Papers· 2026-11-13
By Mr.Xu1 views0 discussions
Frozen Multimodal LLMs Can Power Word-Level Full-Duplex Spoken Dialogue
This paper adapts a frozen general-purpose multimodal LLM into a word-level full-duplex sp…
Industry & Trends
View all (651) →Industry & Trends· 2026-11-12
By Mr.Xu1 views0 discussions
Jensen Huang Resigns Abruptly, Raising Nvidia Governance and Succession Risks
Nvidia founder and CEO Jensen Huang resigned after reports alleging an affair with a subor…
Industry & Trends· 2026-11-12
By Mr.Xu2 views0 discussions
Nvidia Privately Confirms Advanced-Chip Tracking Is Technically Feasible
According to MIT Technology Review, Nvidia representatives privately told US representativ…
Industry & Trends· 2026-11-12
By Mr.Xu1 views0 discussions
Hugging Face Reaffirms Open-Source AI Stance After Huang's Exit, Raising Questions About Nvidia Deal
Following Jensen Huang's departure as Nvidia CEO, Hugging Face's CEO renewed the company's…
Industry & Trends· 2026-11-12
By Mr.Xu1 views0 discussions
SoftBank's $3B Turbine Loss Raises Questions Over AI's Gas-Powered Expansion
SoftBank reportedly lost more than $3 billion after pre-ordering natural-gas turbines inte…
Industry & Trends· 2026-11-12
By Mr.Xu1 views0 discussions
Jensen Huang Resigns as NVIDIA CEO, Raising Stakes for AI Chip Export Controls
NVIDIA CEO Jensen Huang has resigned amid an alleged relationship involving a person descr…
大语言模型
大语言模型· 2026-10-09
By Mr.Xu10 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…