Cosmos3 Action Viewer
🤖
23
Explore interactive visualizations with Viser
Abdul Muhit Temongmere PRO
abdulMuhit
AI & ML interests
None yet
Recent Activity
liked a Space about 3 hours ago
nvidia/Cosmos3-Action-Viewer liked a model 1 day ago
SupraLabs/Supra-A2A-Nano-Exp liked a model 1 day ago
SupraLabs/supra-title-50M-pre-ggufOrganizations
None yet
liked a
Space about 3 hours ago
liked 4
models 1 day ago
SupraLabs/Supra-A2A-Nano-Exp
Any-to-Any • 29.7M • Updated • 23
SupraLabs/supra-title-50M-pre-gguf
Text Generation • 51.8M • Updated • 1.16k • 14
SupraLabs/Supra-50M-Reasoning
Text Generation • 51.8M • Updated • 3.76k • 47
SupraLabs/Supra-1.5-50M-Instruct-exp
Text Generation • 51.8M • Updated • 1.37k • 46
liked a
Space 2 days ago
liked 8
Spaces 3 days ago
LTX-2.3 Spatial Upscaler
🔬
7
2x/4x video upscaling with LTX-2.3 IC-LoRAs
LTX-2.3 Water Simulation
🌊
8
Add water VFX to video with an LTX-2.3 IC-LoRA
Neural DOOM
💀
6
Play classic Doom in your browser with neural‑network CPU emulation
Noir Verdict
🕵
6
Interrogate suspects and solve noir mysteries
mAIndlock
🧠
9
Escape room where every NPC is a mortal mind of tiny LLMs
Peek & Seek
🎯
7
Two AI agents play hide-and-seek and learn between rounds
CODA
🎵
10
AI that finishes the song you quit on.
Tutori — Your Whiteboard Tutor
✏
8
Voice tutor that sketches on a whiteboard while it talks
reacted to Anran-MLLM's post with 🔥 3 days ago
Post
3539
🚀 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
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
reacted to Jaward's post with 🔥 6 days ago
Post
9101
Our preprint is out!
We attempt to model human teaching behaviors into agents yielding a unified framework that enables adaptive personalized learning experiences:
LectūraAgents addresses the prevailing limitations in current AI learning systems with three essential capabilities:
(1) a hierarchical multi-agent architecture modeled on academic standards. we observe that agents collaborating across hierarchies yield better personalized learning outcomes.
(2) an adaptive embodied teaching mechanism, in which the instructor agent executes visible and pedagogically motivated teaching actions (e.g. handwrite, highlight, circle etc) on contents in a teaching environment while speaking.
(3) to achieve this we propose a novel teaching action-speech alignment algorithm (TASA) that dynamically aligns speech with visual teaching actions: specifically, TASA temporally chops up speech segments into word-level tokens, performs salience heuristics analysis on learning contents (texts, images etc) then identifies relevant regions to apply pedagogical teaching actions that guide attention and augment understanding.
We conducted several experiments to assess these capabilities: starting with pedagogical evaluation of the various components under frontier models, comparative analysis with existing frameworks and an efficacy study with real students.
Results show consistent gains in standard instructional metrics (curated by expert educators) spanning lecture content quality, embodied teaching quality, assessment, and personalization over baseline systems, positioning LectūraAgents as a pedagogically grounded framework for personalized learning at scale.
Paper: LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching (2606.16428)
Data: Jaward/lectura-agents-data
We attempt to model human teaching behaviors into agents yielding a unified framework that enables adaptive personalized learning experiences:
LectūraAgents addresses the prevailing limitations in current AI learning systems with three essential capabilities:
(1) a hierarchical multi-agent architecture modeled on academic standards. we observe that agents collaborating across hierarchies yield better personalized learning outcomes.
(2) an adaptive embodied teaching mechanism, in which the instructor agent executes visible and pedagogically motivated teaching actions (e.g. handwrite, highlight, circle etc) on contents in a teaching environment while speaking.
(3) to achieve this we propose a novel teaching action-speech alignment algorithm (TASA) that dynamically aligns speech with visual teaching actions: specifically, TASA temporally chops up speech segments into word-level tokens, performs salience heuristics analysis on learning contents (texts, images etc) then identifies relevant regions to apply pedagogical teaching actions that guide attention and augment understanding.
We conducted several experiments to assess these capabilities: starting with pedagogical evaluation of the various components under frontier models, comparative analysis with existing frameworks and an efficacy study with real students.
Results show consistent gains in standard instructional metrics (curated by expert educators) spanning lecture content quality, embodied teaching quality, assessment, and personalization over baseline systems, positioning LectūraAgents as a pedagogically grounded framework for personalized learning at scale.
Paper: LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching (2606.16428)
Data: Jaward/lectura-agents-data
- 1 reply
liked a
model 8 days ago
liked a
model 21 days ago
reacted to sergiopaniego's post with ❤️ 22 days ago
Post
6272
new banger blog alert 🚨
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
find it here: https://huggingface.co/blog/torch-profiler
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
torch.profiler from scratch. reading tables and traces, overhead bound vs compute bound, the full dispatch chain from python to gpu kernels, and what torch.compile is actually fusing under the hoodfind it here: https://huggingface.co/blog/torch-profiler
- 1 reply
liked a
model 23 days ago
