The No AI Slop Manifesto
The No AI Slop manifesto was introduced by Dex in the closing keynote at AIE CODE after cosignatures from conference speakers and is published at slopmanifesto.com. It is intended as a discussion tool for teams, and the...
Explore tools, prompts, skills, news and resources related to benchmark 第4页.
Latest articles, prompts, use cases and editorial content about benchmark 第4页
The No AI Slop manifesto was introduced by Dex in the closing keynote at AIE CODE after cosignatures from conference speakers and is published at slopmanifesto.com. It is intended as a discussion tool for teams, and the...
This paper introduces Agentic Semi-Supervised Learning (AgentSSL), which frames semi-supervised learning as a program search problem and tests MLE agents under scarce labeled data and abundant unlabeled data. The agents...
Researchers introduced GeoWorld, a controllable geographic environment platform for LLM agents, and LiveGeo, a benchmark for evaluating reliable decision-making as real-world geographic states evolve. LiveGeo requires ag...
This paper examines how user adaptivity complicates evaluation of interactive LLM systems, since users change their prompts and tasks after observing model responses. It distinguishes between common-distribution and indu...
Researchers introduce MAPE, a framework that evolves complete agent memory programs from minimal seeds using a standardized lifecycle interface and an iterative diagnosis-proposal loop. On LoCoMo and LongMemEval, MAPE re...
Researchers introduce a benchmark that injects objective, localizable errors of four types at three severity levels into real papers and measures reviewer detection by error type and severity, along with false-positive r...
AURA 2.0 is a streaming video large language model that introduces Model-Initiated Conversation, allowing it to identify discussion-worthy topics in an evolving video stream and start interactions without a user query. I...
The paper introduces LEAD-RL, a joint main-agent/subagent training framework for multi-agent deep-research systems that uses contribution-aware credit assignment. A training-time rubric scores the research utility of eac...
Skill Adapter is a new system that enables LLM agents to personalize and route general-purpose skills in long-horizon tasks. It distills user-specific adjustments into Adapters linked to base skills, and a routing agent...
AnalogLayoutWorld is an open-source benchmark with 40 expert-reviewed tasks for end-to-end analog circuit layout generation from fixed transistor-level netlists. It integrates a design environment with physical and post-...
This paper tests whether language models can compile known game mechanics directly into neural network weights, without training, using 20 unpublished ARC-AGI-3-style game families. With a fixed 57k-parameter recurrent a...
Lara Mini Base is a 7.2B-parameter mixture-of-experts model with 0.6B active parameters, trained from scratch on 6T tokens spanning English and 44 other languages, covering all 24 official EU languages. It supports 128k-...
The paper introduces S1-Evo, an attack framework targeting typed System-1 decision models used in LLM agents for routing, moderation, and authorization. S1-Evo perturbs untrusted fields through contract-aware evidence ch...
Researchers introduce SPADE, a framework that detects AI-generated text by measuring how well a prompt explains a candidate text using a Pointwise Mutual Information term. SPADE trains one soft prompt per class and predi...
AWS announces the availability of OpenFold3-preview on Amazon SageMaker JumpStart, enabling deployment of the open-source biomolecular structure prediction model with a few lines of code. The model predicts 3D structures...
AWS describes a deployable sample that routes coding-agent requests on Amazon Bedrock through LiteLLM and NVIDIA NeMo Switchyard. The sample offers Stage routing between a capable Claude model and a lower-cost Nemotron m...
This paper introduces Decentralized Primal Averaging (DPA), a decentralized learning algorithm that combines primal averaging with a local quasi-global momentum buffer to handle highly heterogeneous data. It establishes...
Researchers introduce DashBench, a benchmark for evaluating Video Large Language Models on rare and safety-critical driving scenarios. It tests 25 Video LLMs on 1,709 curated driving videos covering collision-related and...
Researchers describe Scale-Induced Semantic Shift (SISS), a security failure mode in which image resizing or compression changes machine-readable semantics and makes hidden textual instructions recoverable after aggressi...
AWS describes SageMaker HyperPod Data Capture, which records live inference inputs and outputs to Amazon S3 at three independent tiers: SageMaker endpoint, load balancer, and model pod. The post walks through Tier 3 capt...