6. FACTS Leaderboard Google introduces the FACTS Leaderboard, a comprehensive benchmark suite for evaluating LLM factuality across diverse scenarios.
GENERATIVE AI
-
Vision-Language Synergy for Abstract Reasoning Tasks
By
–
7. Vision-Language Synergy Reasoning A method that combines visual and textual reasoning to improve performance on ARC-AGI abstract reasoning tasks.
-
DeepCode: Autonomous Framework for Synthesizing Complete Codebases
By
–
3. DeepCode DeepCode is a fully autonomous framework for synthesizing complete codebases from scientific papers despite LLM context limitations.
-
Top AI Papers Week: Agents, LLMs and Vision-Language Models
By
–
Top AI Papers of the Week (Dec 15 – 21): – DeepCode
– FrontierScience
– FACTS Leaderboard
– Detailed Balance in LLM Agents
– Budget Aware Test-time Scaling
– Vision-Language Synergy Reasoning
– Stronger Normalization-Free Transformers Read on for more: -
FeRA: Fine-Tuning Diffusion Models by Frequency Alignment
By
–
What if you could fine-tune a diffusion model by simply following its natural "frequency rhythm"? FeRA is here. It's a new framework that tunes AI image generators by aligning updates with the model's intrinsic frequency energy—how it naturally builds details from blurry to
-
LLM Prompt Demo and AI Agents Insights
By
–
Prompt and demo by @EHuanglu.
— Charly Wargnier (@DataChaz) 21 décembre 2025
If you found this useful, a like or RT goes a long way.
Follow me → @datachaz for insights on LLMs and AI agents 🦾 https://t.co/bfmWTo4gbfPrompt and demo by @EHuanglu
. If you found this useful, a like or RT goes a long way. Follow me → @datachaz for insights on LLMs and AI agents -
Gemini 3 Generates Interactive 3D AR Game with Hand Gesture Recognition
By
–
Gemini 3 absolutely blows ChatGPT 5.2 out of the water… it's not even close.
— Charly Wargnier (@DataChaz) 21 décembre 2025
With one prompt, it generates a fully interactive 3D AR shooting game 🤯
Using the camera, it recognizes hand gestures like index finger aiming, thumb pulling the trigger to shoot.
Prompt in 🧵↓ pic.twitter.com/0MkVpQT5PnGemini 3 absolutely blows ChatGPT 5.2 out of the water… it's not even close. With one prompt, it generates a fully interactive 3D AR shooting game Using the camera, it recognizes hand gestures like index finger aiming, thumb pulling the trigger to shoot. Prompt in ↓
-
Google releases MCP repository for AI agent integration
By
–
Link to the repo:
→ http://
github.com/google/mcp -
vLLM-Omni: Multi-Modal Framework for Text, Image, Video, Audio
By
–
vLLM just got a major upgrade! Originally built for autoregressive text-based LLM serving, vLLM-Omni now lets you serve text, image, video, and audio models – all from a single framework. You can also serve diffusion models for fast parallel generation. 100% open-source.
-
LLMs Give the Impression of Knowing More Than You Really Do
By
–
LLMs are great at giving you the impression that you know more than you really do, and of course they will always praise your crazy ideas