Pai 的 AI 雷达
今天：Click here to，Terms of Service。并行还有 Google brings AI、GitHub Copilot weekly、Build from Source。
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that oft
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that oft
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are
AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to in
AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to in
AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity: age
AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity: age
As large language models (LLMs) become increasingly capable, the long-term value of AI systems depends not only on solving individual requests, but also on transforming experience and accumulated knowledge into durable, reusable competence. We introduce SimSkill, a self-evolving
Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a workin
Reliable transport models are essential when modelling and optimising many chemical engineering processes, yet, most models assume hand-picked constitutive laws which may not reflect reality, and often assume initial conditions are known exactly. Both restrictions can significant
Zero-shot vision-language models (VLMs) are increasingly used as training-free species recognizers, but reported accuracy can reflect more than visual species knowledge. We audit CLIP, BioCLIP, BioCLIP2, and a multilingual Jina CLIP v2 control on seven freshwater-fish categories
RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where environment interaction dominates wall-clock cost. Replay can reduce this burden by reusing past trajectories, but existing method
I finally got access to GPT 6 Astra and Claude Fable 5.1. I wanted to see how far we've come. I was inspired by the "pelican riding on a bicycle" test but wanted to push it a bit more in the direction of inter-object physics, so I came up with this idea for a perpetual slinky goi
AI agents increasingly gather evidence, invoke tools, apply constraints, and produce decisions that people or software may commit to action. A final output alone cannot show which evidence, tool state, rule, authorization, or action path produced it. We present DNative-Twin, a gr
Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substantial challenges in clinical practice. Despite recent advances, existing Multimodal Large Language Models (MLLMs) face two key limitations in neonatal diagnosis: (1) domain gap arisi
Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit pre
In this paper we study linear non-Gaussian acyclic models (LiNGAM) when used in federated environments. These causal models allow one to go beyond Markov equivalence. However, in many domains data are scarce, and increasing the sample size by centralising data from different clie
In the natural sciences, symmetries and cause-effect relationships are ubiquitous. Yet for complex machine-learning tasks, like world-modeling in reinforcement learning, they appear difficult to harness. We propose a formal description of statistical systems based on symmetries i
Clinical trials in the UK can cost up to £1.3 million, with approximately 90% drug failure rate. Toxicity is a major contributing factor in drug failure. Testing is time and cost intensive. In recent years, the use of artificial intelligence has been increasingly explored to aid
Just tried OpenAI Astra , I thought I will never say this , it’s lit , OpenAI cooked something spectacular, and I have a strong feeling this will pull lot of Fable 5 users towards it , and it’s fast, not sure if it’s AGI, but it feels fresh and a very very serious competition to
Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain audio. However, real-world manipulated audio can exhibit mixed authenticity, where genuine and manipulated cues coexist across temporal transitions, overlapping sources, or both.
Artificial intelligence (AI) teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization. This study presents a prompt-engineering-based framework for personalizing general-purpose LLM/RAG-based AI teach
Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental