Clarify: Improving Model Robustness With Natural Language Corrections Lee et al.: https://
arxiv.org/abs/2402.03715 #ArtificialIntelligence #DeepLearning #MachineLearning
RESEARCH
-
Clarify: Improving Model Robustness With Natural Language Corrections
By
–
-
Mistral-7B KVCache Optimization for XLA Compilation
By
–
hey @fchollet . I think this is tricky to do in general (like a no free lunch way).
I think the Mistral-7B implementation KerasNLP writes out a KVCache (for compiler optimization) and specifically writes code in a way that is needed for XLA Compilation to work well.
Do let me -
DiPPeR: Diffusion-Based 2D Path Planning for Legged Robots
By
–
DiPPeR: Diffusion-based 2D Path Planner applied on Legged Robots Liu et al.: https://
arxiv.org/abs/2310.07842 #ArtificialIntelligence #DeepLearning #MachineLearning -
1-Bit Neural Networks: Not New, Earlier Research from 2016
By
–
1-bit neural nets are not new. Earlier papers from 2016: Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 https://
arxiv.org/abs/1602.02830 Ternary Neural Networks for Resource-Efficient AI Applications https://
arxiv.org/abs/1609.00222 -
UC Berkeley and AUTOLab celebrate major achievement
By
–
Congratulations! Go Bears! @UCBerkeley @AUTOLab_Cal
-
Redefining Magic: Write Access to Reality’s Fabric
By
–
My operational definition of magic is “write access to the fabric of reality”. Some people mean “something that cannot be done”. Neither interpretation makes sense?
-
Understanding LLM Behavior: Why Experts Still Have Knowledge Gaps
By
–
A reminder that even the best experts on LLMs don’t really understand all their behaviors (in this case, why AIs often seem a bit preachy & condescending). Lots left to learn.
-
Vision Models: Unlocking New Possibilities in AI
By
–
Using vision models effectively is a massive unlock for instance.
-
Maximizing Existing Models Over Chasing New Arrivals
By
–
A significant oversight I often see is the overemphasis on the arrival of new models, while underestimating the transformative possibilities that lie in creatively fusing together the models we already have
-
Understanding Consistent Behavior Across Independent Language Models
By
–
I’d love to understand this better too… I thought it was just a quirk of the specifics of labeling instructions, but then multiple (what I think should be mostly independent) language models seem to all do this.