Presenting: The Most Important Vision Papers of 2024 as picked by @roboflow and @vikhyatk The biggest trends are: 1. Vision and are converging -> Sora and OpenSora were built with Diffusion Transformers and MagViT
-> @nikhilaravi extended SAM from images to video 2.
RESEARCH
-

Most Important Computer Vision Papers 2024 Trends
By
–
-
Fine-tuning LLMs for RAG: Advanced Techniques
By
–
Good morning! In this week's iteration, let’s dive into fine-tuning LLMs for RAG! https://
open.substack.com/pub/louisbouch
ard/p/fine-tuning-llms-for-rag?r=25qlky&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
… -
2024 AI Research Papers Compilation and Recovery Update
By
–
Thanks for all the warm wishes, everyone! I couldn’t write my yearly AI research review, but here’s my list of bookmarked papers you might find useful: https://
magazine.sebastianraschka.com/p/llm-research
-papers-the-2024-list
… And no worries, I’m slowly but steadily recovering & already starting to feel bit better every day -
Mathematical Reasoning in Multimodal LLMs: Comprehensive Survey
By
–
9). A Survey of Mathematical Reasoning in the Era of Multimodal LLMs – presents a comprehensive survey analyzing mathematical reasoning capabilities in multimodal large language models (MLLMs), covering benchmarks, methodologies, and challenges across 200+ studies since 2021.
-
Precise Length Control in LLMs: Countdown Positional Encoding
By
–
10). Precise Length Control in LLMs – adapts a pre-trained decoder-only LLM to produce responses of a desired length; integrates a secondary length-difference positional encoding into the input embeddings which enables counting down to a user-set response terminal length.
-

DeepSeek-VL2: Advanced Vision-Language Model with Dynamic Tiling
By
–
7). DeepSeek-VL2 – a new series of vision-language models featuring dynamic tiling for high-resolution images and efficient MoE architecture, achieving competitive performance across visual tasks.
-
AutoFeedback: Two-Agent AI System for Science Assessment Feedback
By
–
8). AutoFeedback – a two-agent AI system that generates more accurate and pedagogically sound feedback for student responses in science assessments, significantly reducing common errors like over-praise compared to single-agent models.
-
Text-Attributed Graphs: Automatic Textual Descriptions for Graph Nodes
By
–
4). Graphs to Text-Attributed Graphs – automatically generates textual descriptions for nodes in a graph which leads to effective graph to text-attributed graph transformation; evaluates the approach on text-rich, text-limited, and text-free graphs, demonstrating that it enables
-
Alibaba Releases Qwen2.5 LLM Series with Competitive Performance
By
–
5). Qwen-2.5 Technical Report – Alibaba releases Qwen2.5, a new series of LLMs trained on 18T tokens, offering both open-weight models like Qwen2.5-72B and proprietary MoE variants that achieve competitive performance against larger models like Llama-3 and GPT-4.
-
PAE: Autonomous AI Agent Learning Through Web Navigation
By
–
6). PAE (Proposer-Agent-Evaluator) – a learning system that enables AI agents to autonomously discover and practice skills through web navigation, using reinforcement learning and context-aware task proposals to achieve state-of-the-art performance on real-world benchmarks.