←Search results

Search “Multimodal”

By relevance · Total 16 results Clear search

Wednesday

  1. Smart City Industry Analysis

    A Beauty Company's FDE Implementation in Practice: An Eight-Step Pipeline for Cleaning Massive Multimodal Data into Trustworthy Data

    A beauty company's FDE implementation project processes text, image, audio, and video data collected from Xiaohongshu, Douyin, WeChat Channels, and Weibo through eight steps: defining data specifications, preserving original content, mapping data relationships, multimodal normalization, conflict and quality cleaning, generating structured data, performing acceptance checks, and ingesting according to rules and versions. The original article emphasizes that cleaning results must not overwrite the original text, and that OCR, ASR, and model labels are only added results; it also describes the practice of tracing back to the original evidence when ASR and OCR values conflict, and placing cases that cannot be confirmed into a pending-verification queue. This pipeline has also been organized by the author into a general solution reusable in scenarios such as consumer goods insights, automotive word-of-mouth, restaurant site selection, and brand public opinion.

    A beauty company's FDE implementation project processes text, image, audio, and video data collected from Xiaohongshu, Douyin, WeChat Channels, and Weibo through eight steps: defining data specifications, preserving original content, mapping data relationships, multimodal normalization, conflict and quality cleaning, generating structured data, performing acceptance checks, and ingesting according to rules and versions. The original article emphasizes that cleaning results must not overwrite the

    Matched fieldsTitle、Summary、Body

    #industry#Tutorials / practice#English text is being prepared.#Multimodal
  2. FactRelated story

    Miles summarizes the eight-step multimodal data cleaning solution for FDE at beauty companies

    On October 28, 2026, Miles summarized an eight-step multimodal data cleaning solution for FDE implementation projects at beauty companies. The solution processes text, image, audio, and video data collected from Xiaohongshu, Douyin, WeChat Channels, and Weibo through eight steps: defining data specifications, preserving original content, mapping data relationships, multimodal normalization, conflict and quality cleaning, generating structured data, performing acceptance checks, and storing data by rules and versions. The original text emphasizes that cleaning results must not overwrite the original text, and that OCR, ASR, and model labels serve only as newly added results; when ASR and OCR values conflict, the original evidence is traced back, and if it cannot be confirmed, the item enters a pending-verification queue. This pipeline has also been organized into a general solution that can be reused in scenarios such as consumer goods insights, automotive word-of-mouth, restaurant site selection, and brand public opinion.

    Matched fieldsTitle

    View story:Miles summarizes the eight-step multimodal data cleaning solution for FDE at beauty companies

  3. Full Artificial Analysis articleSelected

    Gemini 4 Carbon Tops the Artificial Analysis Intelligence Index v5

    Google's Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5 with a score of 59, leading in four of the 9 evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA. On the Coding Agent Index, Gemini 4 Carbon (high) paired with the Antigravity CLI scores 59, trailing Claude Code paired with Claude Opus 5.5 (max, 62 points) by 3 points. The model has a 1M-token context window, supports text, image, video, and speech input, and is priced at a standard rate of $4/$20 per million input/output tokens; it is currently available to select users with a 50% discount.

    Google's Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5 with a score of 59, leading in four of the 9 evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA. On the Coding Agent Index, Gemini 4 Carbon (high) paired with the Antigravity CLI scores 59, trailing Claude Code paired with Claude Opus 5.5 (max, 62 points) by 3 points. The model has a 1M-token context window, supports text, image, video, and speech input, and is priced at a

    Matched fieldsBody

    #company#Evaluations / benchmarks#Google#Reasoning

Tuesday

Tuesday

Thursday

Monday

  1. The Beijing News

    Hands-on comparison of three AI office apps: Doubao Work, Qwen Office, and WorkBuddy

    Reporters from The Beijing News Shell Finance conducted a series of hands-on task tests on three AI office apps—Doubao Work, Qwen Office, and WorkBuddy—using the Doubao 2.1 Lite0921, Qwen3.87-Max, and Hy4 preview models, respectively. In the long-horizon task from the "2026 AI Office Sector Research Report," Doubao Work produced 10,000 words in 20 minutes 46 seconds, WorkBuddy produced 25,000 words in 21 minutes 18 seconds, and Qwen Office took over 1 hour to produce 50,000 words but consumed about 1,800 tokens, roughly 60 times that of the other two, requiring the reporter to top up 78 yuan to purchase a membership. In the multimodal tests, Doubao Work's poster and video had the highest degree of completion, and the 3D model generated by WorkBuddy was the closest to the original figurine, but when generating a comic it mistook its own icon for a teal pig face.

    Reporters from The Beijing News Shell Finance conducted a series of hands-on task tests on three AI office apps—Doubao Work, Qwen Office, and WorkBuddy—using the Doubao 2.1 Lite0921, Qwen3.87-Max, and Hy4 preview models, respectively. In the long-horizon task from the "2026 AI Office Sector Research Report," Doubao Work produced 10,000 words in 20 minutes 46 seconds, WorkBuddy produced 25,000 words in 21 minutes 18 seconds, and Qwen Office took over 1 hour to produce 50,000 words but consumed ab

    Matched fieldsSummary、Body

    #chinese#Evaluations / benchmarks#Agents#Multimodal

Thursday

Friday

  1. Story1 reports · 1 facts

    Miles summarizes the eight-step multimodal data cleaning solution for FDE at beauty companies

    On October 28, 2026, Miles summarized an eight-step multimodal data cleaning solution for FDE implementation projects at beauty companies. The solution processes text, image, audio, and video data collected from Xiaohongshu, Douyin, WeChat Channels, and Weibo through eight steps: defining data specifications, preserving original content, mapping data relationships, multimodal normalization, conflict and quality cleaning, generating structured data, performing acceptance checks, and storing data by rules and versions. The original text emphasizes that cleaning results must not overwrite the original text, and that OCR, ASR, and model labels serve only as newly added results; when ASR and OCR values conflict, the original evidence is traced back, and if it cannot be confirmed, the item enters a pending-verification queue. This pipeline has also been organized into a general solution that can be reused in scenarios such as consumer goods insights, automotive word-of-mouth, restaurant site selection, and brand public opinion.

    On October 28, 2026, Miles summarized an eight-step multimodal data cleaning solution for FDE implementation projects at beauty companies. The solution processes text, image, audio, and video data collected from Xiaohongshu, Douyin, WeChat Channels, and Weibo through eight steps: defining data specifications, preserving original content, mapping data relationships, multimodal normalization, conflict and quality cleaning, generating structured data, performing acceptance checks, and storing data

    Matched fieldsTitle

  2. Latent Space

    Elorian Releases DecoyCount Benchmark: Frontier Models All Score Below 50% on Visual Counting Accuracy

    Elorian and Mercor jointly released the DecoyCount benchmark, which tests whether models truly count objects or rely on visual shortcuts. Frontier models all scored below 50% accuracy, with the highest being GPT-6 Astra at 43.17%. Elorian says its visual reasoning model Glimpse scored 50.48% in a single run on 1,660 questions, making it the only model to exceed 50%, but this result comes from internal testing and did not use an agent or tool framework, whereas the six models in the paper each took the average of three runs. Elorian CEO Andrew Dai said the benchmark examines both vision and reasoning, and can distinguish whether a model failed to see the objects or miscounted them.

    Elorian and Mercor jointly released the DecoyCount benchmark, which tests whether models truly count objects or rely on visual shortcuts. Frontier models all scored below 50% accuracy, with the highest being GPT-6 Astra at 43.17%. Elorian says its visual reasoning model Glimpse scored 50.48% in a single run on 1,660 questions, making it the only model to exceed 50%, but this result comes from internal testing and did not use an agent or tool framework, whereas the six models in the paper each to

    Matched fieldsBody

    #newsletter#Evaluations / benchmarks#Multimodal#Reasoning

Saturday

  1. Story1 reports · 1 facts

    Kimi K3.1 Pro ranks 8th on WebDev Arena

    Moonshot AI releases Kimi K3.1 Pro, which ranks 8th on Code Arena WebDev with a score of 1692. According to Arena, its score ties with Claude Opus-5 (Max) at 70% lower cost, and it rises 9 places from Kimi K3 (Max)'s 17th place. The model is priced at $2/$10 per million input/output tokens, with a median cost per task of $1.23, 29% lower than Kimi K3, and its weights will be opened on November 4. Kimi officially calls it a 3T-class open-weight model, featuring a 1M token context and a 2.8T total parameter/104B activated parameter MoE multimodal architecture, with hallucination rate reduced by 65%. Testing Catalog reports that Kimi thus returns to the top 4 in the Code Arena WebDev lab rankings, and says that after the open-weight release it will become the top-ranked open-source model on that leaderboard.

    Moonshot AI releases Kimi K3.1 Pro, which ranks 8th on Code Arena WebDev with a score of 1692. According to Arena, its score ties with Claude Opus-5 (Max) at 70% lower cost, and it rises 9 places from Kimi K3 (Max)'s 17th place. The model is priced at $2/$10 per million input/output tokens, with a median cost per task of $1.23, 29% lower than Kimi K3, and its weights will be opened on November 4. Kimi officially calls it a 3T-class open-weight model, featuring a 1M token context and a 2.8T total

    Matched fieldsSummary

Thursday

  1. Artificial AnalysisSelected

    Gemini 4 Carbon Tops the Artificial Analysis Intelligence Index…

    Artificial Analysis evaluations show that Google's Gemini 4 Carbon tops Intelligence Index v5 with 59 points, ranking first in four of the 9 evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA. On the Coding Agent Index, Gemini 4 Carbon (high) paired with Antigravity CLI scores 59 points, 3 points behind Claude Code paired with Claude Opus 5.5 (max, 62 points). The model is currently available only to some users and has not yet been publicly released; it is priced at $4/$20 per 1M input/output tokens with a 50% discount, has a 1M-token context window, and supports text, image, video, and voice input.

    Artificial Analysis evaluations show that Google's Gemini 4 Carbon tops Intelligence Index v5 with 59 points, ranking first in four of the 9 evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA. On the Coding Agent Index, Gemini 4 Carbon (high) paired with Antigravity CLI scores 59 points, 3 points behind Claude Code paired with Claude Opus 5.5 (max, 62 points). The model is currently available only to some users and has not yet been publicly released; it is p

    Matched fieldsBody

    #editorial#Evaluations / benchmarks#Reasoning#English text is being prepared.

Tuesday

  1. Fireworks AI

    Fireworks Offers Free Training of Muse Glimmer 30B: Using SFT to Predict Kalshi Market Outcomes

    Fireworks AI announced that Muse Glimmer 30B can be trained with SFT for free until November 30, and released a complete recipe for a prediction experiment using historical Kalshi market data. The fine-tuned Glimmer achieved 58.3% accuracy on unseen topics, 11.2 percentage points higher than Jev's 47.1%; in a historical backtest, a hypothetical $1,000 grew to $1,071 after accounting for simulated fees, while both base Glimmer and Jev lost money. Training used LoRA adapters and a K-way cross-entropy loss, ran through the training data only once, and separately used a calibration set to fit a temperature parameter for each question category.

    Fireworks AI announced that Muse Glimmer 30B can be trained with SFT for free until November 30, and released a complete recipe for a prediction experiment using historical Kalshi market data. The fine-tuned Glimmer achieved 58.3% accuracy on unseen topics, 11.2 percentage points higher than Jev's 47.1%; in a historical backtest, a hypothetical $1,000 grew to $1,071 after accounting for simulated fees, while both base Glimmer and Jev lost money. Training used LoRA adapters and a K-way cross-entr

    Matched fieldsBody

    #editorial#Product updates#English text is being prepared.#Open-source ecosystem
  2. Shao Meng

    MIT Course MAS.S62: Two Lectures on the Evolution of Harnesses and Multi-Agent Systems

    Lectures 4-5 of the MIT course MAS.S62 "How to AI an AI" focus on Harness evolution, covering the evolution of harness components, memory, tools, and skills, as well as the evolution of planning, task decomposition, and multi-agent systems. The memory section uses a three-axis taxonomy to connect MemGPT, mem0, MEM1, and Reflexion/ExpeL, and uses CLM to unify context management as file operations; the tools section moves from Toolformer, ToolLLM, and CodeAct to Meta-Harness, which represents the entire harness as a file system and provides about 400 times the amount of feedback information of previous methods. The multi-agent section presents five empirical findings, including that MAS wins 81% on decomposable tasks and loses 70% on tasks with sequential dependencies, and that CORAL achieves new SOTA on 8 tasks, with multi-agent evolution improving over single-agent by 4%-20%.

    Lectures 4-5 of the MIT course MAS.S62 "How to AI an AI" focus on Harness evolution, covering the evolution of harness components, memory, tools, and skills, as well as the evolution of planning, task decomposition, and multi-agent systems. The memory section uses a three-axis taxonomy to connect MemGPT, mem0, MEM1, and Reflexion/ExpeL, and uses CLM to unify context management as file operations; the tools section moves from Toolformer, ToolLLM, and CodeAct to Meta-Harness, which represents the

    Matched fieldsBody

    #hot-signal#Tutorials / practice#Agents#English text is being prepared.

Monday

  1. Artificial AnalysisSelected

    MiniMax-M3.1-Flash scores 42 on the Artificial Analysis Intelligence Index

    MiniMax-M3.1-Flash scores 42 on the Artificial Analysis Intelligence Index, 13 points higher than MiniMax-M3, at less than half the latter's per-task cost. It scores 48% on Humanity's Last Exam and 22% on CritPt, both higher than GLM-5.3-Flash and Gemini 3.8 Flash, and slightly lower than DeepSeek V4.1 Flash 1017. The model has a 1M-token context window, supports text and image input, is priced at $0.15/$0.60 per 1M input/output tokens, and its weights are currently closed-source; MiniMax announced that it will open the weights on October 23.

    MiniMax-M3.1-Flash scores 42 on the Artificial Analysis Intelligence Index, 13 points higher than MiniMax-M3, at less than half the latter's per-task cost. It scores 48% on Humanity's Last Exam and 22% on CritPt, both higher than GLM-5.3-Flash and Gemini 3.8 Flash, and slightly lower than DeepSeek V4.1 Flash 1017. The model has a 1M-token context window, supports text and image input, is priced at $0.15/$0.60 per 1M input/output tokens, and its weights are currently closed-source; MiniMax announ

    Matched fieldsBody

    #editorial#Evaluations / benchmarks#Reasoning#DeepSeek
  2. MarkTechPost

    TinyFish Makes Search Free: Breaking Down the Real Cost of AI Agents Reading Web Pages

    TinyFish announced that, within limits, it will waive retrieval fees for Search and Fetch: Search is limited to 30 requests per minute and 500 per hour, while Fetch is limited to 150 URLs per minute and 1,000 per day. The article notes that free retrieval does not eliminate the inference costs of downstream models; the same article of about 4,300 characters returns an estimated 1,184 to 42,774 tokens across different providers, and three pages of unfiltered content can fill a 128K context window. In the September 28, 2026 Artificial Analysis snapshot, TinyFish Search scored 71 at $9.30 per 1,000 tasks, the lowest total cost among the displayed configurations but also the lowest score, with about 59 seconds per task.

    TinyFish announced that, within limits, it will waive retrieval fees for Search and Fetch: Search is limited to 30 requests per minute and 500 per hour, while Fetch is limited to 150 URLs per minute and 1,000 per day. The article notes that free retrieval does not eliminate the inference costs of downstream models; the same article of about 4,300 characters returns an estimated 1,184 to 42,774 tokens across different providers, and three pages of unfiltered content can fill a 128K context window

    Matched fieldsBody

    #ai-vertical#Product updates#Search#English text is being prepared.