I don't feel like I've fine-tuned myself in any substantial way on ARC more like a bit of few-shots
LLMS
-
AGI-Level Models May Not Need Task-Specific Fine-Tuning
By
–
people commenting that it's normal to train on the train set but somehow I would have expected/hoped that as we're nearing AGI-level capabilities we would not need to really fine-tune/specifically train the model on any specific downstream task, at most a bit of few-shots
-
Open-Source Advantage in Large Language Models Debate
By
–
The Open-Source Advantage in Large Language Models (LLMs) Large Language Models (LLMs) are revolutionizing natural language processing, but the debate between closed-source and open-source models raises important questions about transparency, accessibility, and ethics.
-
LLM Agents Evolve Cooperation Through Indirect Reciprocity
By
–
Cultural Evolution of Cooperation among LLM Agents A study examining how large language model (LLM) agents evolve cooperation and social norms over generations, specifically focusing on indirect reciprocity. Problem: Limited understanding of how multiple LLM agents interact
-
Adaptive Computation Modules: Efficient Token-Level Conditional Inference
By
–
Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference A neural network module that dynamically adapts computational load per token, reducing inference costs without sacrificing accuracy. Problem: Transformer models are computationally
-
MetaMorph: Multimodal LLM Extension via Instruction Tuning
By
–
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning A method to extend LLMs for unified visual and textual generation, leveraging instruction tuning for efficient multimodal adaptation. Problem: Unified models for visual understanding and generation
-
LlamaFusion Extends LLMs with Multimodal Capabilities
By
–
LlamaFusion Extends pretrained text-only LLMs with multimodal capabilities while preserving language performance. Problem:
Training multimodal models from scratch is costly and risks degrading pretrained language abilities. Method:
Adds image-specific modules to pretrained -
LMAgent: Multimodal Large-Scale Multi-User Simulation Framework
By
–
LMAgent: A Large-Scale Multimodal Agents Society for Multi-user Simulation A scalable framework for simulating dynamic, multimodal multi-user behavior using large-scale multimodal LLMs. Problem: Existing LLM-based multi-agent systems simulate only text-based interactions
-
Best-of-N Jailbreaking Method Bypasses Major AI Models
By
–
Best-of-N Jailbreaking Introducing a black-box method that jailbreaks AI models across text, vision, and audio by applying simple prompt augmentations. BoN achieves high success rates, such as 89% on GPT-4o and 78% on Claude 3.5 Sonnet, with 10,000 augmented prompts, and also
-
Confusion Over o1 vs o1 Pro Model Claims
By
–
Part of the reason this is so confusing IMO is they don’t make the same claim about o1 pro, which is still a mystery modification to the purely autoregressive o1. All they’ve really said about pro I think is that it’s not merely o1 with higher reasoning_effort.