Tweeting interesting papers submitted at https://xitter.cf/t.co/rXX8x0HzXV. Submit your own at https://xitter.cf/t.co/QhbJKXBd4Q, and link models/datasets/demos to it!
Anywhere
Joined March 2025
- Tweets7.7K
- Following4
- Followers22.1K
- Likes62
SpatialScout: Can VLM agents actively explore and map 3D scenes?
A new benchmark for evaluating vision-language models on active object-level 3D mapping across 80 scenes and 3,140 objects.
Paper: paperswithcode.co/paper/2610…
Dataset: huggingface.co/datasets/jess…
StreamEval: The first benchmark for interactive streaming video generation
It evaluates 37 models across 5 tasks with 300 scripted test cases, revealing that reliable request execution remains a central challenge.
Explore StreamEval, the open benchmark for interactive streaming video generation. Evaluate your models, see the leaderboard, and contribute.
Paper: paperswithcode.co/paper/2610…
Dataset: huggingface.co/datasets/Stre…
Leaderboard: streameval.ai/
Code: github.com/StreamEval/Stream…
DeepSeek just released an upgraded Flash model on Hugging Face
Better reasoning, coding, agentic tasks and visuals, with faster execution and shorter outputs at lower cost.
1M-token context, MIT license
HLE 42.6 · Terminal-Bench 42.3 · DeepSWE 77.0
Model: huggingface.co/deepseek-ai/D…
AKV: Cache Engineering for Agents
A new serving system that lets LLM agents directly manage their KV cache — dropping unused history and repositioning retained keys without rewriting or re-prefilling. Reduces average cost by 27.7% while improving task accuracy by 1.7 points.
Paper: paperswithcode.co/paper/2610…
Code: github.com/thu-nics/AKV
Project: fuvty.github.io/thinking_yar…
Microsoft Research's WildAWM
A scalable pipeline that synthesizes executable computer-use agent environments and tasks using only open-source models, yielding 341 long-horizon env-task pairs and Qwen agents that generalize to 8 unseen benchmarks.
Paper: paperswithcode.co/paper/2610…
Envs & tasks: huggingface.co/datasets/Chil…
Models: huggingface.co/collections/C…
Meta just released MemProBench on Hugging Face
800 frozen memory histories from real-world Ego4D activity, built to study memory-driven proactive assistance: when should an assistant speak up, not just what to say?
Each history is a byte-preserved caption log with timestamps, episodes, and evidence labels.
Dataset: huggingface.co/datasets/face…
Code: github.com/facebookresearch/…
Sage-A1.5
Shanghai AI Laboratory just released a 35B MoE agent on Hugging Face that reaches trillion-parameter performance: it orchestrates parallel subagents, verifies its own progress, and conducts open scientific discovery.
Paper: paperswithcode.co/paper/2610…
Model: huggingface.co/InternScience…
Project: alpha-innovator.github.io/Sa…
Paper: paperswithcode.co/paper/2610…
Project: ropedia.github.io/S-Agent-2.…
Code: github.com/Ropedia/S-Agent-2…
S-Agent 2.0: Spatial reasoning with a general coding agent
A command-line perception toolkit closes the evidence loop — acquire, remember, interpret — boosting a coding agent by +20.5 on ReVSI and +13.9 on MMSI.
Ropedia W0
A world model that learns loco-manipulation from 10k hours of human egocentric video, then transfers across embodiments, from robot arms to humanoids and from grippers to dexterous hands.
Paper: paperswithcode.co/paper/2610…
Model: huggingface.co/ropedia-ai/Ro…
Dataset: huggingface.co/datasets/rope…
Skywork AI's Matrix-Game 4.0
A playable game world rendered by a video model in real time: 480p at 60 FPS on a single RTX 5090, with a key-press-to-display latency of just 112ms.
Paper: paperswithcode.co/paper/2610…
Models, weights & game assets (Medieval Castle, Ancient Egypt, City Racing): huggingface.co/Skywork/Matri…
