Ofer Hasson

hassonofer's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 21 hours ago

birder-project/lw_detr_2stg_objects365-coco_pe_spatial_s16

Object Detection • Updated about 21 hours ago • 48

updated a model about 22 hours ago

birder-project/deformable_detr_boxref_coco_convnext_v2_tiny_imagenet21k

Object Detection • Updated about 21 hours ago • 25

published a model 3 days ago

birder-project/lw_detr_2stg_objects365-coco_pe_spatial_s16

Object Detection • Updated about 21 hours ago • 48

updated a model 3 days ago

birder-project/lw_detr_2stg_objects365_pe_spatial_s16

Object Detection • Updated 3 days ago • 157

updated a Space 9 days ago

Running

Agents

1

Birder Object Detection

🌐

1

An interactive demo for Birder (object detection)

published a model 10 days ago

birder-project/lw_detr_2stg_objects365_pe_spatial_s16

Object Detection • Updated 3 days ago • 157

updated a model 10 days ago

birder-project/rope_vit_m14_swiglu_avg_eva-bio

Image Feature Extraction • Updated 10 days ago • 41

published a model 10 days ago

birder-project/rope_vit_m14_swiglu_avg_eva-bio

Image Feature Extraction • Updated 10 days ago • 41

updated a model 10 days ago

birder-project/rope_vit_s14_swiglu_avg_eva-bio

Image Feature Extraction • Updated 10 days ago • 58

published a model 10 days ago

birder-project/rope_vit_s14_swiglu_avg_eva-bio

Image Feature Extraction • Updated 10 days ago • 58

liked a model 11 days ago

allenai/Olmo-3.1-32B-Instruct

Text Generation • 32B • Updated Jan 5 • 15.5k • 80

upvoted a collection 11 days ago

Olmo 3.1

Collection

The latest members of the Olmo 3 family: another 3 weeks of RL for 32B Think, the 32B Instruct model, large post-training research datasets... • 9 items • Updated Dec 23, 2025 • 54

updated a model 15 days ago

birder-project/rope_i_vit_l14_nf_swiglu_c1_eva02-clip

Image Feature Extraction • Updated 15 days ago • 48

published a model 15 days ago

birder-project/rope_i_vit_l14_nf_swiglu_c1_eva02-clip

Image Feature Extraction • Updated 15 days ago • 48

upvoted a collection 16 days ago

Perception Encoder

Collection

OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated Sep 19, 2025 • 8

reacted to Anran-MLLM's post with 👍 16 days ago

view post

Post

3563

🚀 Introducing PerceptionDLM — the first multimodal diffusion LLM for parallel region perception!

Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩

✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced

🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM

📊 Benchmark
MSALab/ParaDLC-Bench

📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM

Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨

#multimodal #diffusion #VLM #perception

See translation

🔥

8

8

👍

2

2

+

Reply

liked a model 17 days ago

MiniMaxAI/MiniMax-M3

Image-Text-to-Text • 427B • Updated 7 days ago • 234k • • 1.3k

updated a Space 19 days ago

Running

Agents

5

The Birder Leaderboard

🏆

5

Explore and compare Birder model performance across benchmarks

liked a model 19 days ago

zai-org/GLM-5.2

Text Generation • 753B • Updated 5 days ago • 282k • • 3.57k

updated a model 19 days ago

birder-project/rope_vit5_reg4_b16_nepa-bio

Image Feature Extraction • Updated 19 days ago • 52