Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
Paper • 2604.05083 • Published
AI & ML interests
CVPR Demo Track @ CVPR 2022
Recent Activity
View all activity
gagan3012
authored a
paper 22 days ago
Post
5379
Want to share my enthusiasm for zai-org/GLM-5.1 here too 🔥
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai🚀🚀
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai🚀🚀
- 4 replies
abidlabs
updated a
Space about 1 month ago
gagan3012
authored 2
papers about 1 month ago
gagan3012
submitted 2
papers to Daily Papers about 2 months ago
elischwartz
authored 12
papers about 2 months ago
FETA: Towards Specializing Foundation Models for Expert Task Applications
Paper • 2209.03648 • Published
Teaching Structured Vision&Language Concepts to Vision&Language Models
Paper • 2211.11733 • Published
Teaching VLMs to Localize Specific Objects from In-context Examples
Paper • 2411.13317 • Published
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Paper • 2502.09927 • Published
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
Paper • 2502.12342 • Published • 7
DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers
Paper • 2505.22584 • Published
Advancing Speech Understanding in Speech-Aware Language Models with GRPO
Paper • 2509.16990 • Published • 22
ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation
Paper • 2507.19492 • Published • 1
CLIMP: Contrastive Language-Image Mamba Pretraining
Paper • 2601.06891 • Published • 3
CARES: Context-Aware Resolution Selector for VLMs
Paper • 2510.19496 • Published • 9
NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning
Paper • 2404.00459 • Published
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
Paper • 2509.21153 • Published • 1
Post
6890
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.
Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
- 3 replies