Papers.Data.Code
The Weekly ML Signal
Selected, not collected.
Weekly edition · Nov 02 – Nov 08 · Issue #12
Real-world agent evaluation
Long-horizon benchmarks, tool-use trajectories, and robot action labels.
Top 3 papers
- Proving and Improving the Platonic Representation Hypothesis with JEPAs→
It proves cross-modal JEPA encoders align up to rotation and beats 72B LMs with 42x fewer samples.
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation→
It pipelines denoising with cache refresh to stream one video chunk per forward pass.
- VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation→
It benchmarks autonomous code-written MP4 generation in 1-hour sandboxes with evidence-based grading across 239 tasks.
Top 3 repos
- hyz317/HairDeck→
Unlike most single-image 3D tools, it outputs hair cards, spring-bone rigs, and GLB/VRM exports together.
- wangzan101/Mika→
Runs a cross-app Android agent entirely on-device, including background-screen execution and user handoff.
- inclusionAI/IDM→
Uses internal EMA feature-moment matching to reach 94.25% LongText-CN in two steps.
Top 3 datasets
- Axion1-0/axion-training-data→
Unlike mostly evaluation benchmarks, it releases 18,363 full agent-training trajectories plus 484 RL tasks with verified tool-use.
- InternRobotics/RoboAtom→
Aggregates 12 robot datasets into 100K-1M time-aligned atomic action annotations with a 500-trajectory held-out segmentation-and-description benchmark.
- google/physical-engineerings-last-exam→
Unlike recent agent benchmarks, it evaluates long-horizon engineering deliverables in realistic multi-tool CAD, BIM, and simulation workspaces.
One useful ML email a week.
The Weekly ML Signal.
Worth your time, not all of your time.
We track new ML work across papers, code, and data, then keep only the pieces worth a closer look. Selected, not collected.