ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Paper • 2607.04438 • Published • 49
Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
upvoted a paper about 8 hours ago
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog upvoted a paper about 9 hours ago
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference reacted to PhysiQuanty's post with 🔥 about 9 hours ago
🧠 Arithmetic-SLM : A 30M model that manages to compute simple arithmetic better than a 3B model 🚀
https://huggingface.co/WhirlwindAI/Arithmetic-SLM
https://huggingface.co/spaces/WhirlwindAI/arithmetic-slm
🏆 Leaderboard ArithMark-2 🏆
🥇 Qwen/Qwen2.5-Math-1.5B = 82.08%
🥈 WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
🥉 Qwen/Qwen2.5-3B = 78.44%
Example WhirlwindAI/Arithmetic-SLM =
0.5 * 0.5 = 0.25 ✅
105 + 45 / 8 = 110 ✅
(132 / 12) + (46 - 15) = 42 ✅
(10 + 28) * 3 = 114 ✅
1 * (16 + 28) = 44 ✅
(21 + 27) * (14 - 7) = 336 ❌
```python
leaderboard = """
| Model | Params | Score |
|----------------------------------|--------------|-----------|
| Qwen/Qwen2.5-Math-1.5B | 1.54B | 82.08% |
| WhirlwindAI/Arithmetic-SLM | 31.70M | 78.60% | <=
| Qwen/Qwen2.5-3B | 3.09B | 78.44% |
| Qwen/Qwen2.5-1.5B | 1.54B | 77.72% |
| Qwen/Qwen2.5-Coder-1.5B | 1.54B | 74.88% |
| HuggingFaceTB/SmolLM2-1.7B | 1.71B | 66.12% |
| Qwen/Qwen2.5-0.5B | 494M | 63.04% |
| facebook/MobileLLM-R1-140M-base | 140M | 53.88% |
| SupraLabs/Supra-50M-Base | 52M | 27.12% |
"""
```
Bench =
https://huggingface.co/datasets/AxiomicLabs/ArithMark-2.0
DataSet =
https://huggingface.co/datasets/WhirlwindAI/Arithmetic
By Science AND FOR SCIENCE <3 Organizations
upvoted a paper about 8 hours ago
upvoted a paper about 9 hours ago
upvoted a paper about 15 hours ago
upvoted 3
papers about 17 hours ago
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Paper • 2607.04439 • Published • 41
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Paper • 2607.05155 • Published • 12
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Paper • 2607.05061 • Published • 17
upvoted 3
papers about 18 hours ago
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Paper • 2607.01764 • Published • 6
GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving
Paper • 2602.11688 • Published • 5
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Paper • 2607.04428 • Published • 15
upvoted 4
papers about 19 hours ago
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Paper • 2607.04425 • Published • 63
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Paper • 2607.02881 • Published • 7
LLM-as-a-Verifier: A General-Purpose Verification Framework
Paper • 2607.05391 • Published • 10
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Paper • 2607.01793 • Published • 7
upvoted 4
papers 1 day ago
Measuring the Gap Between Human and LLM Research Ideas
Paper • 2607.01233 • Published • 12
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Paper • 2606.25178 • Published • 7
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Paper • 2607.01420 • Published • 11
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Paper • 2607.02461 • Published • 33
upvoted 3
papers 2 days ago
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Paper • 2607.02501 • Published • 49
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Paper • 2607.01804 • Published • 27
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Paper • 2606.31227 • Published • 12