2026年7月20日 技术热点总结

项目简介：V- Modal AI: Search anything anywhere SDK Flutter

技术栈：Dart

核心介绍：VModal for Flutter Give your Android and iOS apps a multimodal memory. Upload video. Find moments by meaning, speech, text, or imagery. Keep the experience fast, native, and 100% Flutter. Turn every video library into an experience your users can explore. VModal brings multimodal video search and mobile-friendly uploads to Dart with a small, typed API. Your app owns the interface; the SDK handles the VModal gateway, request models, responses, upload streams, progress, and cancellation.

项目数据：⭐ 580 …

项目简介：🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

技术栈：Python

核心介绍：> “Most people do not know that they can just point their agents at my writing, > tweets, podcasts, and talks and improve the output of their agents by 100x.” > — [Ryan Lopopolo] Harness engineering, the practice of improving agent output by shaping the environment around it, holds a chosen model and coding agent constant as a black box. It improves the two external levers—context and tools—and curates the environment around them. The worker should be able to recover…

项目简介：Circuit Framework — multi-agent LLM trading research system

技术栈：Python

核心介绍：A crypto-native multi-agent research and paper-trading framework where specialized agents analyze market structure, derivatives, sentiment, catalysts and market regime before a deterministic risk engine approves or rejects each trade. Circuit Framework is a fork of TradingAgents (Apache 2.0). The internal Python package remains tradingagents for compatibility; user-facing branding, CLI help and crypto workflows are Circuit Framework.

项目数据：⭐ 485 Stars，🍴 19 Forks

A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes human vision distinctly different from most popular computer vision models in use today, which input images globally and in a single shot. A natural question therefore is whether local, sequential vision models may provide any fundamental computational benefits in addition to being biologically more plausible than global models. In this work, we investigate this question from the perspective of visual state track…

We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets to determine whether its ga…

Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts…

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR o…

Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination. Unlike vision-language models that emphasize scene understanding and textual decision making, or generative world models that mainly predict future visual states, RxBrain represents embodied plans in a single planning sequence where language and visual imagination play complementary roles. Language provides the abstract structure of a plan, including task…

In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and crucially (b) incorporates a new notion of per-token times, with some tokens proceeding from noise to token at a faster rate than others. Continuous space modeling helps TTCD avoid the parallel sampling of multiple tokens, which is a key source of inaccuracy at high speedups for models that iterate purely in discrete space. The notion of per-token times helps TT…