· ai
I Built a TUI to Visualize RAG Chunking because chunk_size=1000 is a Lie 📉
Let’s be honest for a second. When you are building a RAG Retrieval-Augmented Generation pipeline, how do you pick your chunk_size and overlap? If you are like...
-
- · ai
[Paper] MOA: Multi-Objective Alignment for Role-Playing Agents
Role-playing agents (RPAs) must simultaneously master many conflicting skills -- following multi-turn instructions, exhibiting domain knowledge, and adopting a ...
- · ai
[Paper] BAMBO: Construct Ability and Efficiency LLM Pareto Set via Bayesian Adaptive Multi-objective Block-wise Optimization
Constructing a Pareto set is pivotal for navigating the capability-efficiency trade-offs in Large Language Models (LLMs); however, existing merging techniques r...
- · ai
[Paper] BAMBO: Construct Ability and Efficiency LLM Pareto Set via Bayesian Adaptive Multi-objective Block-wise Optimization
Constructing a Pareto set is pivotal for navigating the capability-efficiency trade-offs in Large Language Models (LLMs); however, existing merging techniques r...
- · ai
RoboCrop: Teaching robots how to pick tomatoes
Article URL: https://phys.org/news/2025-12-robocrop-robots-tomatoes.html Comments URL: https://news.ycombinator.com/item?id=46218782 Points: 3 Comments: 0...
- · ai
[Paper] Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dra...
- · ai
ChatGPT is Apple’s most downloaded app of 2025 in the US
This is ChatGPT's first year as the No. 1 app on the U.S. App Store by downloads....
- · ai
How to Maximize Agentic Memory for Continual Learning
Learn how to become an effective engineer with continual learning LLMs The post How to Maximize Agentic Memory for Continual Learning appeared first on Towards...
- · ai
The AI that scored 95% — until consultants learned it was AI
Presented by SAP When SAP ran a quiet internal experiment to gauge consultant attitudes toward AI, the results were striking. Five teams were asked to validate...
- · ai
[Paper] Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
Equivariant neural networks encode symmetry as an inductive bias and have achieved strong empirical performance in wide domains. However, their expressive power...
- · ai
[Paper] SynthPix: A lightspeed PIV images generator
We describe SynthPix, a synthetic image generator for Particle Image Velocimetry (PIV) with a focus on performance and parallelism on accelerators, implemented ...
- · ai
Google launches sub-$5 AI Plus plan in India to compete with ChatGPT Go
For new users in India, Google is offering an AI Plus subscription for ₹199 $2.21 for the first six months, after which you'll have to pay ₹399 $4.44....