Termsslug: zero-shot-learning

Zero-shot Learning

零样本学习

Ability to perform new tasks without task-specific fine-tuning

Curated Intelligence

17 items · Page 1/2
Marktechpost (@Marktechpost)T2·Tools
72 pts
Google Research Releases Agile Deliberation Framework for Human-AI Concept Definition

Google Research has open-sourced Agile Deliberation, a framework that lets users define fuzzy 'gray area' concepts before an AI classifier learns them. The system splits a concept into in-scope and out-of-scope subconcepts, surfaces borderline samples for user labeling, and has Gemini rewrite the definition as a VLM prompt. Across 18 live sessions it beat zero-shot Gemini 2.5 Flash by 10.5 F1 points on average, with code released under Apache 2.0.

IT之家 · 智能时代T2·Agents
68 pts
Unitree CEO: G1 Sales Hit 10k, Zero-Shot LLMs Control Robots

Unitree founder Wang Xingxing revealed that the G1 humanoid robot has produced 10,000-20,000 units, making it the world's best-selling model. Tests show frontier LLMs like GPT-6 can directly control robots for tasks like painting and Go without training. The company is developing a self-evolving system called 'Unitree Preview', aiming for voice-controlled task completion by next year.

Hacker News AIT2·Tools
68 pts
Developer Creates Adversarial Language to Test LLM Coding Limits

A developer introduced KillSwitch, an esoteric programming language designed to probe whether LLMs truly understand code logic or rely on pattern matching from training data. By embedding hidden lies in the spec and exploiting weaknesses like character counting and safety guardrails, it serves as an adversarial benchmark for testing coding agents' robustness.

量子位官网T2·Agents
68 pts
Magic Atom's EchoPolicy-0 Tops MolmoSpaces with 75.4% Success Rate, Validating Zero-Shot Embodied Agent Generalization

Magic Atom's VLM Agent framework EchoPolicy-0 ranked first on the global MolmoSpaces benchmark with a 75.4% average success rate, while its sibling framework MagicBrain secured fourth place. This achievement marks a shift from 'demo-ready' to 'production-ready' embodied intelligence, validating the effectiveness of hierarchical architectures and instruction-following capabilities in complex zero-shot environments.

IT之家 · 智能时代T2·Models
68 pts
Huawei and ECNU Launch Qiyao Time-Series Foundation Model: Tops TIME-leaderboard and GIFT-Eval with Zero-Shot Prediction and Low-Cost Fine-Tuning

Huawei Cloud and East China Normal University have launched the 'Qiyao' Ascend-native time-series foundation model, which has topped the prestigious TIME-leaderboard and GIFT-Eval (Pretrained category). Deeply optimized for the Huawei Ascend ecosystem, the model offers high accuracy and robustness, supporting zero-shot prediction for scenarios like power grids and finance, while enabling low-cost fine-tuning for vertical industry customization.

机器之心 (微信公众号)T2·Models
85 pts
OpenAI Releases 722 Math Proofs Including Quasi-Riemann Hypothesis

OpenAI released a GitHub repository containing 722 mathematical manuscripts generated by an unreleased internal model, tackling major problems like the Quasi-Riemann Hypothesis and 4D Kakeya Conjecture. Sam Altman described this as the dawn of a new era of discovery, sparking significant interest in both AI and mathematics communities.

Google ResearchT1·Models
68 pts
Bypassing Inference Bottlenecks with Retrieve-for-Train

To address high inference costs in complex AI search caused by query decomposition, the 'Retrieve-for-Train' method is proposed. It replaces zero-shot LLM dynamic planning with retrieval-augmented training, significantly reducing reliance on expensive thinking budgets for efficient set retrieval.