Authors: || Published: 2024-10-26T17:55:00 || Updated: 2024-10-26T17:55:00
Recent AI Reading [26 October 2024]
Papers
Agentic AI
- Agentic Information Retrieval
- Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
AI Alignment with Human Feedback and Preferences, and other methods
- Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
- Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
- Aligning Large Language Models via Self-Steering Optimization
- Learning Goal-Conditioned Representations for Language Reward Model
- Scalable Ranked Preference Optimization for Text-to-Image Generation
- MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
Model Evaluation
- Large Language Model Evaluation via Matrix Nuclear-Norm
- HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks
- MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures
- NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
- CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution
- Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
- M-RewardBench: Evaluating Reward Models in Multilingual Settings
- TP-Eval: Tap Multimodal LLMs’ Potential in Evaluation by Customizing Prompts
Miscellaneous
- CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
- The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
- BitNet: Scaling 1-bit Transformers for Large Language Models
Articles and Blog Posts
- Artificial + Human Intelligence Merge in the World of Process Safety Systems
- Introducing Multimodal Embed 3: Powering AI Search
Miscellaneous
- Swarm - Educational framework exploring ergonomic, lightweight multi-agent orchestration