RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
Paper • 2610.27782 • Published • 5
AI & ML interests
Artificial Intelligence
Recent Activity
View all activity
Papers
RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
HuggingFriends
submitted a
paper to Daily Papers 11 days ago
mickyhimself
authored 4
papers 21 days ago
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Paper • 2607.27380 • Published • 55
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Paper • 2608.13560 • Published • 60
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling
Paper • 2610.15166 • Published • 44
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
Paper • 2610.20731 • Published • 34
Karl28
submitted a
paper to Daily Papers 23 days ago
dronefreak
posted an update about 1 month ago
Post
376
🚀 Excited to open-source the Brackish Underwater Object Detection Model Zoo on Hugging Face.
This release includes:
- 🤖 8 YOLOv8, YOLOv11, and YOLOv26 object detection models trained on Brackish, spanning nano through x-large variants (RF-DETR variants to follow once I have the compute for them).
- 🐟 Benchmarked on Brackish's underwater marine-animal detection task — crab, fish, jellyfish, shrimp, small_fish, and starfish, captured 9 meters below the surface under naturally varying visibility conditions.
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices, qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 99.3% (YOLOv8s), 85.65% mAP@50:95, 99.36% precision.
- ⚡ Best efficiency tradeoff: YOLOv26n hits 98.95% mAP@50 at just 6.1 GFLOPs (2.6M params) — within 0.35 points of the top model while using ~4.7x fewer FLOPs (28.6 GFLOPs). The whole zoo actually clusters tightly here (98.74–99.3% mAP@50 across all 8 models), so there's little accuracy left on the table by going small on this dataset.
If you're working on underwater perception, marine biology/ecology monitoring, or robotics in low-visibility environments, I hope these resources are useful.
📦 Dataset:
dronefreak/Brackish
🤖 Model Collection: dronefreak/brackish-underwater-object-detection-model-zoo-6a7c153687b2821da0c6591d
Feedback, bug reports, and contributions are always welcome.
This release includes:
- 🤖 8 YOLOv8, YOLOv11, and YOLOv26 object detection models trained on Brackish, spanning nano through x-large variants (RF-DETR variants to follow once I have the compute for them).
- 🐟 Benchmarked on Brackish's underwater marine-animal detection task — crab, fish, jellyfish, shrimp, small_fish, and starfish, captured 9 meters below the surface under naturally varying visibility conditions.
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices, qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 99.3% (YOLOv8s), 85.65% mAP@50:95, 99.36% precision.
- ⚡ Best efficiency tradeoff: YOLOv26n hits 98.95% mAP@50 at just 6.1 GFLOPs (2.6M params) — within 0.35 points of the top model while using ~4.7x fewer FLOPs (28.6 GFLOPs). The whole zoo actually clusters tightly here (98.74–99.3% mAP@50 across all 8 models), so there's little accuracy left on the table by going small on this dataset.
If you're working on underwater perception, marine biology/ecology monitoring, or robotics in low-visibility environments, I hope these resources are useful.
📦 Dataset:
dronefreak/Brackish
🤖 Model Collection: dronefreak/brackish-underwater-object-detection-model-zoo-6a7c153687b2821da0c6591d
Feedback, bug reports, and contributions are always welcome.
wy1iu
submitted a
paper to Daily Papers about 1 month ago
zhangzhiwei666
authored 4
papers about 1 month ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
Paper • 2609.35954 • Published • 25
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
Paper • 2609.02998 • Published • 16
D$^3$-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
Paper • 2608.24987 • Published • 28
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
Paper • 2601.15625 • Published • 9
dronefreak
posted an update about 1 month ago
Post
136
🚀 Open-sourcing the KITTI Object Detection Model Zoo on Hugging Face.
- 🤖 12 models: YOLOv8, YOLOv9, YOLO11 and YOLO26, from nano/tiny up to x-large.
- 🚗 Street-scene detection: cars, cyclists, pedestrians, vans, trucks and more, in KITTI's ultra-wide frames.
- 📊 Model cards with metrics, per-class results, curves, showcases, a demo video and full configs.
Headline numbers:
- 🏆 Best mAP@50: 43.73% (YOLO26x). Best mAP@50:95: 26.54% (YOLO26s).
- ⚡ YOLO26n gets 42.54% mAP@50 at just 6.1 GFLOPs, within 1.2 points of YOLO26x at ~34x fewer FLOPs.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Andreas Geiger, Philip Lenz and Raquel Urtasun (CVPR 2012). This is an unofficial YOLO-ready reformat (CC BY-NC-SA 3.0). Metrics are on the validation split, since KITTI has no public test labels.
📦 Dataset: dronefreak/KITTI
🤖 Collection: dronefreak/kitti-object-detection-model-zoo-6ab4cb94fb08dccf3bde2e8b
Feedback and contributions welcome.
- 🤖 12 models: YOLOv8, YOLOv9, YOLO11 and YOLO26, from nano/tiny up to x-large.
- 🚗 Street-scene detection: cars, cyclists, pedestrians, vans, trucks and more, in KITTI's ultra-wide frames.
- 📊 Model cards with metrics, per-class results, curves, showcases, a demo video and full configs.
Headline numbers:
- 🏆 Best mAP@50: 43.73% (YOLO26x). Best mAP@50:95: 26.54% (YOLO26s).
- ⚡ YOLO26n gets 42.54% mAP@50 at just 6.1 GFLOPs, within 1.2 points of YOLO26x at ~34x fewer FLOPs.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Andreas Geiger, Philip Lenz and Raquel Urtasun (CVPR 2012). This is an unofficial YOLO-ready reformat (CC BY-NC-SA 3.0). Metrics are on the validation split, since KITTI has no public test labels.
📦 Dataset: dronefreak/KITTI
🤖 Collection: dronefreak/kitti-object-detection-model-zoo-6ab4cb94fb08dccf3bde2e8b
Feedback and contributions welcome.
dronefreak
posted an update about 1 month ago
Post
124
🚀 Open-sourcing the BDD100K Object Detection Model Zoo on Hugging Face.
- 🤖 10 models: YOLOv8/v9/v10/YOLO11/YOLO26 (n/s) and RF-DETR Nano.
- 🚗 Driving-scene detection: 10 classes including traffic lights and signs, across varied weather and lighting.
- 📊 Model cards with metrics, per-class results, curves, showcases, dashcam demo videos and full configs.
Headline numbers:
- 🏆 Best mAP@50: 58.76% (YOLO26s), 33.86% mAP@50:95.
- ⚡ YOLO26n gets 52.25% mAP@50 at 6.1 GFLOPs, ~3.7x fewer than YOLO26s.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Fisher Yu et al. (UC Berkeley, CVPR 2020). It has a non-commercial license, so it is not mirrored; get it from https://www.bdd100k.com/. The "test" split here is BDD100K's official validation set.
🤖 Collection: dronefreak/bdd100k-object-detection-model-zoo-6aafc46f2f6c5e4d8676d894
Feedback and contributions welcome.
- 🤖 10 models: YOLOv8/v9/v10/YOLO11/YOLO26 (n/s) and RF-DETR Nano.
- 🚗 Driving-scene detection: 10 classes including traffic lights and signs, across varied weather and lighting.
- 📊 Model cards with metrics, per-class results, curves, showcases, dashcam demo videos and full configs.
Headline numbers:
- 🏆 Best mAP@50: 58.76% (YOLO26s), 33.86% mAP@50:95.
- ⚡ YOLO26n gets 52.25% mAP@50 at 6.1 GFLOPs, ~3.7x fewer than YOLO26s.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Fisher Yu et al. (UC Berkeley, CVPR 2020). It has a non-commercial license, so it is not mirrored; get it from https://www.bdd100k.com/. The "test" split here is BDD100K's official validation set.
🤖 Collection: dronefreak/bdd100k-object-detection-model-zoo-6aafc46f2f6c5e4d8676d894
Feedback and contributions welcome.
dronefreak
posted an update about 1 month ago
Post
60
🚀 Open-sourcing the UAVDT Object Detection Model Zoo on Hugging Face.
- 🤖 18 models: YOLOv8/v9/v10/YOLO11/YOLO26 (n–m) and RF-DETR Nano/Small/Medium.
- 🚁 Drone traffic surveillance: cars, trucks and buses, mostly tiny objects (median box ~0.14% of the image).
- 📊 Model cards with metrics, per-class results, curves, showcases, demo videos and full configs.
Headline numbers:
- 🏆 Best mAP@50: 33.43% (YOLOv26m). Best mAP@50:95: 20.54% (RF-DETR Medium).
- ⚡ YOLOv26s gets 32.98% mAP@50 at 22.8 GFLOPs, ~3.3x fewer than YOLOv26m.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Dawei Du et al. (ECCV 2018). It is research-only, so I don't mirror it; the dataset repo is a guide to the official source.
📦 Dataset: dronefreak/UAVDT
🤖 Collection: dronefreak/uavdt-object-detection-model-zoo-6aadb3673084702d3ed45ff0
Feedback and contributions welcome.
- 🤖 18 models: YOLOv8/v9/v10/YOLO11/YOLO26 (n–m) and RF-DETR Nano/Small/Medium.
- 🚁 Drone traffic surveillance: cars, trucks and buses, mostly tiny objects (median box ~0.14% of the image).
- 📊 Model cards with metrics, per-class results, curves, showcases, demo videos and full configs.
Headline numbers:
- 🏆 Best mAP@50: 33.43% (YOLOv26m). Best mAP@50:95: 20.54% (RF-DETR Medium).
- ⚡ YOLOv26s gets 32.98% mAP@50 at 22.8 GFLOPs, ~3.3x fewer than YOLOv26m.
Trained and evaluated with DetectionBench: https://github.com/dronefreak/DetectionBench
Dataset credit: Dawei Du et al. (ECCV 2018). It is research-only, so I don't mirror it; the dataset repo is a guide to the official source.
📦 Dataset: dronefreak/UAVDT
🤖 Collection: dronefreak/uavdt-object-detection-model-zoo-6aadb3673084702d3ed45ff0
Feedback and contributions welcome.
donghao-zhou
submitted a
paper to Daily Papers about 1 month ago
Karl28
submitted a
paper to Daily Papers 3 months ago
dronefreak
posted an update 3 months ago
Post
442
🌧️❄️ Free demo: remove rain, raindrops, or snow from a photo with a single model
I put together an unofficial demo for **Histoformer** (ECCV 2024, arXiv: 2407.10172), a 16.6M-parameter transformer that handles three different weather degradations, rain streaks, adherent raindrops, and snow, in one unified model. It uses a "histogram self-attention" mechanism that groups pixels by degradation intensity instead of spatial position, which is a
neat way to sidestep the usual spatial-window tradeoffs in restoration transformers.
Try it here, free on ZeroGPU: dronefreak/histoformer-weather-restoration
Upload a photo and get a before/after slider. Two checkpoints available: one tuned for real-world photos, one for the paper's synthetic benchmarks.
Also put together a cleaner, easy-to-use model card with a copy-pasteable Quickstart if you'd rather run it yourself: dronefreak/Histoformer
This is an unofficial demo/mirror, not affiliated with the original authors. All credit for the actual research goes to Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, and Xiaochun Cao (@sunsean ). Official repo: https://github.com/sunshangquan/Histoformer. Weights are MIT-licensed.
Reported numbers from the paper: 32.1 PSNR on rain+fog (Outdoor-Rain), 33.1 on raindrops, 37.4 / 32.2 on light/heavy snow (Snow100K-S/L).
I put together an unofficial demo for **Histoformer** (ECCV 2024, arXiv: 2407.10172), a 16.6M-parameter transformer that handles three different weather degradations, rain streaks, adherent raindrops, and snow, in one unified model. It uses a "histogram self-attention" mechanism that groups pixels by degradation intensity instead of spatial position, which is a
neat way to sidestep the usual spatial-window tradeoffs in restoration transformers.
Try it here, free on ZeroGPU: dronefreak/histoformer-weather-restoration
Upload a photo and get a before/after slider. Two checkpoints available: one tuned for real-world photos, one for the paper's synthetic benchmarks.
Also put together a cleaner, easy-to-use model card with a copy-pasteable Quickstart if you'd rather run it yourself: dronefreak/Histoformer
This is an unofficial demo/mirror, not affiliated with the original authors. All credit for the actual research goes to Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, and Xiaochun Cao (@sunsean ). Official repo: https://github.com/sunshangquan/Histoformer. Weights are MIT-licensed.
Reported numbers from the paper: 32.1 PSNR on rain+fog (Outdoor-Rain), 33.1 on raindrops, 37.4 / 32.2 on light/heavy snow (Snow100K-S/L).
- 2 replies
dronefreak
posted an update 3 months ago
Post
2,145
🚀 Excited to open-source the SeaDronesSee Object Detection Model Zoo on Hugging Face.
This release includes:
- 🤖 YOLOv8, YOLOv11, YOLOv26 and RF-DETR object detection models trained on SeaDronesSee, spanning nano through x-large YOLO variants plus RF-DETR Nano/Small/Medium.
- 🌊 Benchmarked on SeaDronesSee's maritime search-and-rescue setting — swimmers, boats, jet skis, life-saving appliances and buoys captured by UAVs over open water, at varying altitudes and non-uniform image resolutions (1080p up to 4K+).
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices (YOLO), qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 83.47% (RF-DETR Medium), 47.49% mAP@50:95, 87.01% precision.
- ⚡ Best efficiency tradeoff: YOLOv26s hits 80.14% mAP@50 at just 22.8 GFLOPs (10.0M params) — within ~3 points of the top RF-DETR variant, while actually beating YOLOv11x's 74.82% mAP@50 using ~8.6x fewer FLOPs (196.0 GFLOPs).
The goal is to make benchmarking and experimenting with maritime UAV perception easier by providing ready-to-use pretrained checkpoints, all trained and evaluated under one shared pipeline (DetectionBench: https://github.com/dronefreak/DetectionBench).
Full credit for the underlying dataset goes to Leon Amadeus Varga, Benjamin Kiefer, Martin Messmer, and Andreas Zell (University of Tübingen, WACV 2022) — this release is an unofficial, YOLO-ready reformatting of their work (CC0-licensed), not a new dataset.
If you're working on maritime search-and-rescue, UAV perception, autonomous drones, or real-time object detection, I hope these resources are useful.
📦 Dataset:
dronefreak/SeaDronesSee
🤖 Model Collection: dronefreak/seadronessee-object-detection-model-zoo-6a7b030a25797e5dd2d70123
Feedback, bug reports, and contributions are always welcome.
This release includes:
- 🤖 YOLOv8, YOLOv11, YOLOv26 and RF-DETR object detection models trained on SeaDronesSee, spanning nano through x-large YOLO variants plus RF-DETR Nano/Small/Medium.
- 🌊 Benchmarked on SeaDronesSee's maritime search-and-rescue setting — swimmers, boats, jet skis, life-saving appliances and buoys captured by UAVs over open water, at varying altitudes and non-uniform image resolutions (1080p up to 4K+).
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices (YOLO), qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 83.47% (RF-DETR Medium), 47.49% mAP@50:95, 87.01% precision.
- ⚡ Best efficiency tradeoff: YOLOv26s hits 80.14% mAP@50 at just 22.8 GFLOPs (10.0M params) — within ~3 points of the top RF-DETR variant, while actually beating YOLOv11x's 74.82% mAP@50 using ~8.6x fewer FLOPs (196.0 GFLOPs).
The goal is to make benchmarking and experimenting with maritime UAV perception easier by providing ready-to-use pretrained checkpoints, all trained and evaluated under one shared pipeline (DetectionBench: https://github.com/dronefreak/DetectionBench).
Full credit for the underlying dataset goes to Leon Amadeus Varga, Benjamin Kiefer, Martin Messmer, and Andreas Zell (University of Tübingen, WACV 2022) — this release is an unofficial, YOLO-ready reformatting of their work (CC0-licensed), not a new dataset.
If you're working on maritime search-and-rescue, UAV perception, autonomous drones, or real-time object detection, I hope these resources are useful.
📦 Dataset:
dronefreak/SeaDronesSee
🤖 Model Collection: dronefreak/seadronessee-object-detection-model-zoo-6a7b030a25797e5dd2d70123
Feedback, bug reports, and contributions are always welcome.
- 2 replies
dronefreak
posted an update 3 months ago
Post
1,921
🚀 Excited to open-source the GWHD Wheat Head Detection Model Zoo on Hugging Face.
This release includes:
- 🤖 YOLOv8, YOLOv11, YOLOv26 and RF-DETR object detection models trained on GWHD (Global Wheat Head Dataset), spanning nano through x-large variants across both architecture families.
- 🌾 Benchmarked on GWHD's dense, single-class wheat-head detection task — ~45 annotated heads per image on average, captured across multiple countries, genotypes, and growth stages, a genuinely hard small/dense-object setting.
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices (YOLO), qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 74.25% (YOLOv11x), 34.92% mAP@50:95, 83.37% precision.
- ⚡ Best efficiency tradeoff: YOLOv26s hits 70.49% mAP@50 at just 22.8 GFLOPs (10.0M params) — within ~4 points of the top YOewer FLOPs (196.0 GFLOPs).
The goal is to make benchmarking and experimenting with agricultural computer vision easier by providing ready-to-use pretrained checkpoints, all trained and evaluated under one shared pipeline (DetectionBench: https://github.com/dronefreak/DetectionBench).
Full credit for the underlying dataset goes to Etienne David, Mario Serouart, Simon Madec, and the Global Wheat Head Detection 2020/2021) — this release is anunofficial, YOLO-ready reformatting of their work, not a new dataset.
If you're working on precision at detection, or just want areproducible detector benchmark, I hope these resources are useful.
📦 Dataset:
dronefreak/GWHD
🤖 Model Collection: https://huggingface.co/collections/dronefreak/gwhd-wheat-head-detection-model-zoo-6a7aea28b5431918cc46cec1
Feedback, bug reports, and contributions are always welcome.
This release includes:
- 🤖 YOLOv8, YOLOv11, YOLOv26 and RF-DETR object detection models trained on GWHD (Global Wheat Head Dataset), spanning nano through x-large variants across both architecture families.
- 🌾 Benchmarked on GWHD's dense, single-class wheat-head detection task — ~45 annotated heads per image on average, captured across multiple countries, genotypes, and growth stages, a genuinely hard small/dense-object setting.
- 📊 Detailed model cards with mAP/precision/recall, per-class breakdowns, PR/F1 curves and confusion matrices (YOLO), qualitative detection showcases, and full training configurations for reproducibility.
Headline numbers:
- 🏆 Best mAP@50: 74.25% (YOLOv11x), 34.92% mAP@50:95, 83.37% precision.
- ⚡ Best efficiency tradeoff: YOLOv26s hits 70.49% mAP@50 at just 22.8 GFLOPs (10.0M params) — within ~4 points of the top YOewer FLOPs (196.0 GFLOPs).
The goal is to make benchmarking and experimenting with agricultural computer vision easier by providing ready-to-use pretrained checkpoints, all trained and evaluated under one shared pipeline (DetectionBench: https://github.com/dronefreak/DetectionBench).
Full credit for the underlying dataset goes to Etienne David, Mario Serouart, Simon Madec, and the Global Wheat Head Detection 2020/2021) — this release is anunofficial, YOLO-ready reformatting of their work, not a new dataset.
If you're working on precision at detection, or just want areproducible detector benchmark, I hope these resources are useful.
📦 Dataset:
dronefreak/GWHD
🤖 Model Collection: https://huggingface.co/collections/dronefreak/gwhd-wheat-head-detection-model-zoo-6a7aea28b5431918cc46cec1
Feedback, bug reports, and contributions are always welcome.
- 3 replies