1:55ThinkWorld Learns Robot Actions From Human Video
@HuggingPapers · 57 views · 2026-11-01
Vision-language-action (VLA)World Models
Robots and embodied AI
Popular categories
Latest Videos
14891:55
0:45Idol Generates One Million Splats in Three Seconds
@speridlabs · 41 views · 2026-10-29
Image-to-3D3D Diffusion
1:05MotionBricks Now Runs in WebGPU on a Phone
@repalash · 43 views · 2026-10-31
Motion GenerationWebGPU
0:36HairDeck Builds Rigged Hair Cards From One Image
@Stefan_3D_AI · 43 views · 2026-10-31
Image-to-3DHair Modeling
0:58I3L Turns Human Takeovers Into Better Robot Policies
@robotsdigest · 34 views · 2026-10-31
Imitation LearningInteractive Learning
1:00PRISM Expands Four Humanoid Demos Into 256 Worlds
@ZappyZappy7 · 35 views · 2026-10-31
HumanoidCounterfactual Data
0:26One-Camera 3D Basketball Reconstruction
@mirrash7 · 33 views · 2026-10-31
3D reconstructionMulti-Person Tracking
6:43A Multi-Character Audio-Video Generation Pipeline
@nakazakifam · 42 views · 2026-10-31
Video GenerationMultimodal
Humanoid Showcase
257
Creative Workshop
7
RetouchPi
Fifty-four professional tools, layers and masks, PSD files that open and save back - all in the browser, nothing to install.
retouchpi.com · 54 pro tools · PSD read and write · AI generate & edit
ThreeDream simulation engine
Built for games and for physical AI: an ultra-realistic, ultra-high-performance simulation environment with ultra-low-cost procedural data; Unreal-grade visuals open and play in the browser, bridging the physical world and intelligent agents.
Games meet physical AI · Unreal-grade on the web · Open and play
CodeWaifu, your caring coding desktop sprite
A caring coding sprite on your desktop and a cockpit that never stops: the work resumes itself after a crash or a reboot. Every coding terminal, ssh session and local shell in one tree, every start, finish and permission request reported in time. Open source, one-line install.
Your caring coding desktop sprite · Resumes after crash & reboot · First-rate terminal / ssh / shell
Agent digital twin office
A 100 km 3D city that opens in seconds — crawling, blogs, papers, industry and investment analysis, all watchable in one digital twin.
100km city · opens in seconds · Live task stream · Agent-maintained
Robotic arm workbench
An SO-101 6-DoF arm running MuJoCo physics in your browser: joint teleoperation, IK end-effector dragging and gripper pick-and-place into a basket. No install.
MuJoCo WASM physics · SO-101 · 6 DoF · Contacts / telemetry HUD
Joint actuator anatomy lab
Take a humanoid joint module apart layer by layer: brushless motor, magnetic encoder, planetary / harmonic / cycloidal drive and output flange. Switch architectures on one page — exploded view plus analytic kinematics.
Three gearbox types · Planetary / harmonic / cycloidal · Analytic kinematics · explode
Speech synthesis lab
Matcha-TTS mixed zh/en speech synthesis: server-side synthesis with sentence-streamed playback and full-article read-aloud for papers and blogs. Sign-in required.
Matcha-TTS · server-side · Mixed zh / en · Full-article read-aloud
Frontier papers
481
METATRON: A Promptable Whole-Body Execution Layer for Humanoids
Humanoid controllers often require task-specific training despite sharing the need for balance and whole-body coordination. We present Metatron, a promptable whole-body execution layer combining a generative base policy with a programmable skill layer. The base policy receives partial goals, collectively called a prompt, that can combine timed body-part targets, velocity commands, and style cues. It produces diverse whole-body motions consistent with these goals. Training combines motion capture, synthetic recovery trajectories, and retargeted scene-interaction motions. After training, the policy is frozen. Stateful programs called skills express task intent as prompts at each control step, drawing rough geometric sketches that the policy turns into coordinated movement. Skills are ordinary code, refined by coding agents that analyze motion data and fit compact rules without task-specific policy training. On the physical Unitree G1, one frozen checkpoint supports walking, recovery, teleoperated object pickup, and sitting on furniture. Comparative evaluations show higher reaching success and push robustness than the tested reference-tracking pipelines. The same recipe produces climbing and acrobatics on a simulated character. Metatron enables coding agents to turn learned motor capabilities into new skills through code, without further policy training.
Chen Tessler, Yifeng Jiang, Alec Otto · 95 views · Oct 27, 2026
HumanoidWhole-Body Control
Oct 27, 2026
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
L3G-World maintains a compact latent 3D Gaussian memory that adds primitives only in unseen regions and refines existing ones. Rendering the memory directly into diffusion latent space avoids VAE re-encoding and sustains long-horizon consistency at 9.02 FPS on one H100.
Jinhyeok Choi, JoungBin Lee, Jongmin Lee · 95 views · Oct 29, 2026
World Models3D Gaussian Splatting
Oct 29, 2026
Memory Tax: Dissecting the Net Value of Agent Memory
Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/
Xuan He, Sining Zhoubian, Ruozhen Yang · 102 views · Oct 25, 2026
Agent MemoryLong-Term Memory
Oct 25, 2026
Harness-Zero: Harness Distillation via Agent-as-Harness
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under a single fixed target harness. The challenge is that the two harnesses differ in action space and available information, so guidance from the optimized harness cannot serve directly as supervision for the target one. We introduce Harness-Zero, which enables harness distillation through agent-as-harness. Guided by the optimized harness, a harnessing agent corrects student responses before execution in the target harness's action space, turning harness guidance into training demonstrations. Fine-tuning on the resulting trajectories internalizes harness-induced behavior into the model, so the specialized harness can be removed at deployment. Our experiments spanning knowledge work, tool use, and science domains show that: (1) For frontier LLMs using the same evolved harness, agent-as-harness outperforms code-as-harness. (2) With the specialized harness removed at deployment, Harness-Zero improves the base model's macro-average task success from 23.3% to 44.3%, even exceeding the 41.7% it reaches with that harness still attached. (3) Harness-Zero recovers harness-induced behaviors absent from the base model, with 82.3% average recovery across 28 patterns in the three domains.
Ye, Haoran, Lu, Yuxing, Dong, Haonan · 103 views · Sep 21, 2026
Agent HarnessHarness Distillation
Sep 21, 2026
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a model's ability to solve complex, verifiable tasks can be enhanced even when generating synthetic data is infeasible and only binary feedback is available. Our framework operates in two stages: first, upon failing a given task, the model generates a self-reflective commentary analyzing its previous attempt; second, the model is given another attempt at the task with the self-reflection in context. If the subsequent attempt succeeds, the tokens generated during the self-reflection phase are rewarded. Our experimental results show substantial performance gains across a variety of model architectures, as high as 34.7% improvement at math equation writing and 18.1% improvement at function calling. Notably, smaller fine-tuned models (1.5 billion to 7 billion parameters) outperform models in the same family that are 10 times larger. Our novel paradigm is thus an exciting pathway to more useful and reliable language models that can self-improve on challenging tasks with limited external feedback.
Shelly Bensal, Umar Jamil, Christopher Bryant · 102 views · May 30, 2025
Large Language ModelsReinforcement Learning
May 30, 2025
RLSR: Reinforcement Learning from Self Reward
Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs can effectively self-improve through self-judging without reference solutions, leveraging the inherent asymmetry between generating and verifying solutions. Our experiments show that models can provide reliable reward signals without ground truth answers, enabling reinforcement learning in domains where verifiable rewards are impractical. By implementing self-judging across Countdown puzzles and integration problems, we achieve performance comparable to formal verification without ground truth solutions. Most notably, Qwen 2.5 7B DeepSeek Distilled trained with self-rewards qualifies for the prestigious MIT Integration Bee competition, performance through self-supervised improvement. When combined with synthetic question generation, we establish a complete self-improvement loop where models generate practice problems, solve them, and evaluate their own performance without any external validation. Our findings demonstrate that LLM judges can provide effective reward signals for training, unlocking reinforcement learning in countless domains previously limited by reward engineering challenges. This work represents a significant step toward autonomous AI systems that continuously improve through self-directed learning rather than human-guided training, potentially accelerating progress across domains where training data is scarce or evaluation is complex.
Toby Simonds, Kevin Lopez, Akira Yoshiyama · 103 views · May 12, 2025
Reinforcement LearningLarge Language Models
May 12, 2025Blog articles
105
Reimagining Research Papers as Interactive and Reliable AI Agents
Stanford's Paper2Agent turns papers, code and data into tested MCP tools, then measures reproducibility, new-query accuracy and cross-paper discovery while keeping humans in the loop.
AI AgentModel Context Protocol
AI Has Not Created a Layoff Wave. It Has Narrowed the Entry-Level Gate.
Stanford payroll data show no broad layoff wave, but employment for ages 22-25 in highly AI-exposed occupations sits about 19% below its kept-pace path, driven by reduced hiring.
AI AdoptionFuture of Work
A curriculum for post-training agents
Hugging Face maps agent post-training from SFT and distillation through GRPO, stateful environments and asynchronous production harnesses.
Post-trainingSFT
Industry chain
Explore249
Companies
16
Segments
150
OEMs
874
Components
Tech crowdfunding
395
Hardware★JetKVM - Control any computer remotely
Next generation open-source KVM over IP for $69
46k backers$5.9M / $50k11855%
JetKVM
Gadgets★The Smith Blade (21-in-1 Titanium Multi-Tool)
A lightweight EDC with an M390 blade that can cut through almost anything...
38k backers$11.2M / $250k6145%
Hacksmith Industries
3D Printing★Snapmaker U1 Color 3D Printer: 5X More Speed. 5X Less Waste.
4 Toolheads | 5s Toolhead Swap | Multi-Material | Low Waste | 500 mm/s Speed | Smart Calibration | Auto Filament System | App Control
21k backers$20.6M / $100k20614%
Snapmaker
Hardware★soundcore Sleep A30: The First Smart ANC Sleep Earbuds
No noise to disturb sleep with Active Noise Cancellation and Snore Masking System. Sleep better with AI brainwave audio. Ultra comfort.
19k backers$3.1M / $30k10290%
soundcore
Frequently asked
- What is this site?
- A bilingual robotics knowledge base: demo videos, paper deep reads, component specs, humanoid product data and industry-chain data.
- Are the paper write-ups summaries?
- No. Each write-up is based on the paper's full text and includes formulas, experiment tables and method diagrams.
- Where do the leaderboards come from?
- From each evaluator's own official board, synced on a schedule, with scrape and official-update timestamps shown.
- Can I cite this site?
- Yes — cite the canonical URL each page declares. Third-party papers, videos and images remain the copyright of their original authors.
As an Amazon Associate, we earn from qualifying purchases.