Demos

AIGC demos filed by vertical — agents and LLMs doing real work, world models, AI-made games and design. Each clip carries its vertical and capability domain; pick a chip to narrow the feed.

Waterfall Pagination

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

@axichuhai · 801 views · 2026-09-30

Voice InteractionASR

Temporal cascading of planning and control in one quadrotor MPC: high-fidelity control nearby, point-mass planning far ahead, up to 75% lower closed-loop cost

Temporal cascading of planning and control in one quadrotor MPC: high-fidelity control nearby, point-mass planning far ahead, up to 75% lower closed-loop cost

@davsca1 · 583 views · 2026-09-30

Three open-source tools give your agent full-web data extraction: Agent-Reach, Patchright Enhanced, and Scrapling

Three open-source tools give your agent full-web data extraction: Agent-Reach, Patchright Enhanced, and Scrapling

@liambraus · 1.2k views · 2026-09-30

HarnessOpen Source

Nav Arena "Can Jev Nav?": 133 environments and 2,000+ tasks benchmark System-1 language models driving robots; a WorldState rewrite lifts Jev from 40% to 90%

Nav Arena "Can Jev Nav?": 133 environments and 2,000+ tasks benchmark System-1 language models driving robots; a WorldState rewrite lifts Jev from 40% to 90%

@stash_pomichter · 810 views · 2026-09-30

NavigationBenchmarks

Open Dots launches: Composio's open-source take on OpenAI's Dot resident agent at 1/10th the cost on your Mac

Open Dots launches: Composio's open-source take on OpenAI's Dot resident agent at 1/10th the cost on your Mac

@KaranVaidya6 · 796 views · 2026-09-30

HarnessOpenAI Dot

image-to-3dlab "Pixel Match": free open-source image-to-3D that preserves your source pixels — text, logos and fine detail survive

image-to-3dlab "Pixel Match": free open-source image-to-3D that preserves your source pixels — text, logos and fine detail survive

@Bingeljell · 709 views · 2026-09-30

3D GenerationGraph-to-3D

OTRetarget: joint robot-and-object motion retargeting via optimal transport preserves contacts across morphologies

OTRetarget: joint robot-and-object motion retargeting via optimal transport preserves contacts across morphologies

@CarnErwann · 662 views · 2026-09-30

HumanoidLoco-manipulation

AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed

AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed

@rsasaki0109 · 630 views · 2026-09-30

AgiBot GE-Act 2.0: the first native World Action Model to validate a pretraining and scaling path for embodied AI

AgiBot GE-Act 2.0: the first native World Action Model to validate a pretraining and scaling path for embodied AI

@AGIBOTofficial · 664 views · 2026-09-11

AgiBotAgiBot Robotics

Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)

Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)

@_akhaliq · 707 views · 2026-09-30

Audio8 ASR InfiniteStreaming ASR

SoL-Refiner: one-step refinement turns low-res video into 4K - NVIDIA speed-of-light video refiner

SoL-Refiner: one-step refinement turns low-res video into 4K - NVIDIA speed-of-light video refiner

@HaoZhe65347 · 741 views · 2026-09-30

SoL-RefinerNVIDIA

Lumo humanoid up close: hip-class shoulder motors, sturdy hands, exposed wiring

Lumo humanoid up close: hip-class shoulder motors, sturdy hands, exposed wiring

@ErenChenAI · 710 views · 2026-09-29

HumanoidActuators

As an Amazon Associate, we earn from qualifying purchases.