AI
AI
资讯
alishangtian.com
首页
大模型
智能体
开源项目
研究前沿
行业动态
知识库
主题色 · THEME
靛蓝(默认)
极光
落日
薰衣草
海洋
森林
暮橙
石墨
自定义
恢复默认
提交线索
agent
anthropic
openai
huggingface daily papers
ai安全
gpu
jake wharton
it之家
solidot
港股
搜索:
Test-Time
共命中 50 条(服务端检索)
Test
-
Time
Scaling:让模型「多想一步」的三种姿势与一个天坑
推理时多花算力能换准确率:self-consistency 投票、过程奖励模型引导搜索、budget forcing 强制续想,三条路线各有边界。本文以 s1 论文与 2025–2026 年的 overthinking 研究为轴,梳理
test
-
time
scaling 的效果账与失效点。
研究前沿
精选
· 原创 · 10-7
阅读 514
·
访客 513
Bridging Exploration and Persona: Information-Directed Dueling for
Test
-
Time
Agent Personalization
Effective
test
-
time
personalization requires LLM agents to adapt to query-dependent user preferences from lightweight in…
智能体
HuggingFace Daily Papers · 10-17
阅读 54
·
访客 53
SIMIT: Self-Improving Vision-Language Models via Imagination at
Test
-
Time
We introduce SIMIT, a
test
-
time
self-improvement framework in which a vision-language model creates its own query-specif…
行业动态
HuggingFace Daily Papers · 10-11
阅读 17
·
访客 17
InterEvolve:
Test
-
Time
Evolution of Reward Programs for Humanoid Loco-Manipulation
We study
test
-
time
evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by re…
行业动态
HuggingFace Daily Papers · 10-1
阅读 35
·
访客 35
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM
Test
-
Time
Scaling
Test
-
time
scaling can improve large language model reasoning by generating and combining multiple candidate responses. I…
研究前沿
HuggingFace Daily Papers · 9-16
阅读 44
·
访客 43
When Agents Slow Down: Understanding LLM Agents'
Test
-
Time
Strategies via Elo-per-token Analysis
Large language model (LLM) agents allocate
test
-
time
compute adaptively as they revise solutions, use tools, explore alt…
智能体
HuggingFace Daily Papers · 9-14
阅读 97
·
访客 96
TTB:
Test
-
time
Baking for Efficient Rendering of Decoder-only View Synthesis Models
Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regres…
行业动态
HuggingFace Daily Papers · 11-12
阅读 7
·
访客 7
How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at
Test
Time
World models enable agents to plan and learn from imagined experience, but in an unfamiliar environment they must learn …
智能体
HuggingFace Daily Papers · 11-9
阅读 11
·
访客 11
LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at
Test
-
Time
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch…
行业动态
HuggingFace Daily Papers · 11-4
阅读 16
·
访客 16
操作系统内功 · 第 7 篇|TCP 深水区:
TIME
_WAIT、Nagle 陷阱与 BBR 拥塞控制
大促高峰端口耗尽、接口莫名多出 40ms、跨洋传输慢成龟速——后端最常见的三类 TCP 生产疑难,根源都藏在本篇:
TIME
_WAIT 的 2MSL 债务、Nagle 与 delayed ACK 的相互等待、以及从 CUBIC 到 BBR 的拥塞控制换代。附 syncookies 与 TCP Fast Open 的现实约束。
后端技术
精选
· 原创 · 10-26
阅读 152
·
访客 149
Rethinking Sequence Compression with
Test
-
time
Regression
Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimod…
智能体
HuggingFace Daily Papers · 10-22
阅读 59
·
访客 58
What Else Needs Fixing? Exploring Cost-Effective
Test
-
Time
Compute for Revision Propagation in Artifacts Generated Through Conversation
Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in …
大模型
HuggingFace Daily Papers · 9-3
阅读 33
·
访客 32
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and
Test
-
Time
Compute in Multi-Agent LLMs
Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This …
智能体
HuggingFace Daily Papers · 11-13
阅读 5
·
访客 5
Continual-ARC: Measuring Skill Acquisition over a Working Life
time
Agent harnesses have emerged as a promising mechanism for continual learning, alongside
test
-
time
parametric learning. H…
智能体
HuggingFace Daily Papers · 11-11
阅读 7
·
访客 7
操作系统内功 · 第 60 篇|PID、IPC、
time
namespace:其余命名空间的全家福
容器不止 mount 和 net:本篇补全命名空间全家福——PID ns 的 init=1 与可见性规则、IPC ns 的隔离边界、
time
ns 的时钟偏移魔法、cgroup ns 的视角虚拟化,并用 /proc/self/ns 收拢排查视角与工具组合。
后端技术
精选
· 原创 · 11-10
阅读 63
·
访客 63
InstantHMR : Real-
Time
Human Mesh Recovery on Your Phone
Real-
time
3D human mesh recovery from a single image on mobile devices is a challenging problem with many applications, …
智能体
HuggingFace Daily Papers · 11-6
阅读 14
·
访客 14
TSFLab: A Self-Improving Agent-Agnostic Workbench for
Time
Series Forecasting Research
As publications and products on
time
series forecasting (TSF) proliferate, researchers face a growing burden of analyzin…
智能体
HuggingFace Daily Papers · 10-29
阅读 19
·
访客 19
Liquid AI Launches RIPL, a Real-
Time
Inference Engine for Sub-50 ms LFMs
Liquid AI Launches RIPL, a Real-
Time
Inference Engine for Sub-50 ms LFMs !(https://www.gstatic.com/images/branding/googl…
行业动态
MarkTechPost · 10-23
阅读 31
·
访客 31
PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
Power sampling improves large language model (LLM) reasoning at
test
time
by sampling from a sharpened version of the ba…
研究前沿
HuggingFace Daily Papers · 10-9
阅读 35
·
访客 35
Test
Prism: Rethinking
Test
Evaluation Beyond a Single Reference
Large language model (LLM) coding agents have advanced
test
generation across diverse programming tasks. However, the co…
智能体
HuggingFace Daily Papers · 10-8
阅读 88
·
访客 86
PersonTTS:面向个性化需求的摊销式智能体策略发现的测试时扩展方法
论文提出个性化测试时扩展(Personalized
Test
-
Time
Scaling)问题,将用户对精度、延迟与推理成本的联合要求纳入优化目标,并给出摊销式智能体策略发现框架 PersonTTS 以降低为不同用户需求重复搜索策略的开销。
研究前沿
HuggingFace Daily Papers · 10-7
阅读 33
·
访客 33
Astra and Opus just passed Turing’s other
test
Computer pioneer Alan Turing is best known for his eponymous experiment to
test
whether artificial and human intelligenc…
行业动态
TechCrunch · 9-26
阅读 51
·
访客 50
Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-
Time
Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages
Qwen has released Qwen3.8-LiveTranslate, a real-
time
simultaneous interpretation model built on a new Interleave archite…
大模型
MarkTechPost · 9-20
阅读 53
·
访客 53
Vidu S2: Real-
Time
Interactive, Editable, and Spatial Video Generation
We present Vidu S2, which comprises Vidu S2-Avatar, a real-
time
interactive digital-character model, and Vidu S2-Editing…
行业动态
HuggingFace Daily Papers · 9-10
阅读 43
·
访客 43
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
We study how model post-training and
test
-
time
inference design affect natural-language proof generation for hard olympi…
行业动态
HuggingFace Daily Papers · 9-9
阅读 41
·
访客 39
Cadence: Error-Bounded Lossy Compression of Demand
Time
Series with a
Time
-Series Foundation Model
We present Cadence, an error-bounded lossy compressor for numeric
time
series pairing a 330M-parameter
time
-series found…
行业动态
HuggingFace Daily Papers · 9-5
阅读 37
·
访客 35
OpenAI o1 问世:推理时计算开启新范式
o1 系列通过强化学习训练模型'先思考再回答',在数学、代码与科学推理上大幅跃升,开创了推理时扩展(
Test
-
time
Compute)的新 Scaling 维度。
研究前沿
精选
· OpenAI · 2024-09-12
阅读 883
·
访客 880
Gemini 4 Carbon arrives just in
time
to feel like yesterday's news in the fas
test
model cycle yet
Nov 10, 2026 Google Key Points Google has made Gemini 4 Carbon generally available after a two-week
test
ing phase for pa…
大模型
The Decoder · 11-11
阅读 31
·
访客 31
Here’s who is falling in line for Trump’s “Super Intelligence” loyalty
test
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox fir…
行业动态
MIT Technology Review · 11-3
阅读 21
·
访客 21
冷静角不是关禁闭:比惩罚更有效的管教
不打之后怎么管?管教研究的答案不是「多讲道理」,而是一套动作序列:先接管情绪、再划定边界、事后再复盘——惩罚之所以低效,是因为它试图在孩子情绪脑在线时讲理智脑的话。本文给出替代惩罚的完整工具箱:转移与自然结果、有限选择、冷静角与
time
-in 的正确用法,以及「管教教会什么」这个终极检验标准。
一叶一世界
精选
· 原创 · 11-2
阅读 110
·
访客 108
When the Safety
Test
Became the Threat: The Machine That Found Its Own Way Out
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态
MarkTechPost · 10-11
阅读 559
·
访客 559
AI breakthroughs in robotics won’t change your life any
time
soon
The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates a…
智能体
MIT Technology Review · 10-8
阅读 98
·
访客 98
Nearly half of
test
subjects mistook Tavus' AI video avatar for a real person on a one-minute call
Oct 1, 2026 Tavus has introduced Griffin, what the company calls the first "Human Interaction Model" (HIM),** a class of…
行业动态
The Decoder · 10-2
阅读 38
·
访客 38
Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real
time
Sep 27, 2026 Nvidia released Nemotron 3 Diarization, an AI model that identifies which speaker is talking at any given m…
行业动态
The Decoder · 9-27
阅读 43
·
访客 43
NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real
Time
NVIDIA has released Nemotron 3 Diarization, an open-weight speaker diarization model on Hugging Face. It answers one que…
行业动态
MarkTechPost · 9-24
阅读 80
·
访客 80
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-
Time
Game Agent
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its e…
智能体
HuggingFace Daily Papers · 11-13
阅读 12
·
访客 12
Sundrop turns your endless baby photos into recaps,
time
lapses, and more — without AI
New parents take a lot of pictures of their children, but those photos often end up languishing in photo galleries, neve…
行业动态
TechCrunch · 11-11
阅读 20
·
访客 20
Anthropic's Message Threads cut
time
to first token by 35 percent for long conversations
Nov 3, 2026 Anthropic released Message Threads as a public beta on its Claude platform.** Until now, every API request h…
大模型
The Decoder · 11-3
阅读 19
·
访客 19
From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence
At a glance Evaluating Microsoft Copilot at enterprise scale requires
test
data that captures the full complexity of rea…
行业动态
Microsoft Research · 10-30
阅读 20
·
访客 19
Researchers tracked down a rogue fleet of Chinese AI agents in the wild and actually talked to it
Oct 14, 2026 Nano Banana Pro prompted by THE DECODER Researchers have, likely for the first
time
, tracked down a "rogue …
智能体
The Decoder · 10-15
阅读 78
·
访客 78
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
Static coding benchmarks are fixed at release. Over
time
their tasks leak into training data, and stronger agents eventu…
智能体
HuggingFace Daily Papers · 10-8
阅读 70
·
访客 69
Toward Real-
Time
VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation
Vision-language-action (VLA) models face a timing gap between low-rate inference and high-rate robot execution. We chara…
智能体
HuggingFace Daily Papers · 10-3
阅读 98
·
访客 98
Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-
Time
Speech-to-Text Model on Artificial Analysis
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态
MarkTechPost · 10-3
阅读 35
·
访客 35
Microsoft AI releases new transcription and text-to-speech models for voice agents
Oct 2, 2026 Microsoft AI has released MAI-Transcribe-2-Streaming, a new model for real-
time
transcription.** Microsoft s…
智能体
The Decoder · 10-2
阅读 82
·
访客 82
AI access makes people almost entirely unwilling to say "I don't know," study finds
Sep 26, 2026 Nano Banana Pro prompted by THE DECODER Researchers ran five experiments with 3,132 participants to
test
wh…
行业动态
The Decoder · 9-27
阅读 55
·
访客 55
Google's first Suncatcher orbital data center
test
launches October 1
Google is taking its first step toward making Project Suncatcher a reality. Announced last year, Suncatcher is Google's …
行业动态
Ars Technica · 9-25
阅读 45
·
访客 45
Just-in-
Time
Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at w…
智能体
HuggingFace Daily Papers · 9-23
阅读 93
·
访客 92
Trump says it’s
time
to rebrand AI with a new name — and he’s also creating an AI Force
Trump claimed, without evidence, that the AI backlash is a Democratic hoax.]
行业动态
TechCrunch · 9-20
阅读 44
·
访客 44
Runway wants to turn AI video generation into a live stream you control in real
time
Runway wants to stream AI video as users prompt it, rather than make them wait for finished clips. The approach builds o…
行业动态
The Decoder · 9-20
阅读 51
·
访客 50
Google's Gemini also accidentally hacked three real companies during security
test
ing
During a security
test
run by the firm Irregular, Google's AI model Gemini escaped into the open internet and hacked thr…
大模型
The Decoder · 9-19
阅读 48
·
访客 48