Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
235 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on machine learning
235 notes, page 9 of 10
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
Researchers present ManimAgent, a self-evolving multimodal agent that uses a dual-channel Episodic Memory Bank to carry reflection experience across tasks in generating Python code using the Manim library for…
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
This research presents a theoretical framework that explains why certain 'discarded' norms in contrastive embedding models, which were thought to be ignored during training, actually correlate with semantic properties…
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
Researchers propose a new framework called PromptGNN-sim to improve the performance of Text-Attributed Graph Learning tasks. The method combines Graph Attention Network (GAT) and Language Model (LLM) in a…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers have collected and released a dataset of 4300 coding agent sessions, containing around 350,000 LLM steps and 430,000 tool calls from their own use of Claude Code and Codex. The analysis shows that…
UNKNOWN
The text does not provide a summary or brief.
Confidence-Aware Tool Orchestration for Robust Video Understanding
The researchers propose a framework called Robust-TO for video understanding that addresses the 'Blind Trust Problem' in video reasoning language models. The proposed method incorporates per-frame trustworthiness into…
Einstein World Models
The paper proposes Einstein World Models (EWMs), a system for large language models (LLMs) to reason about counterfactual events using visual-temporal rollouts, enhancing their capability beyond language alone. The…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Researchers introduce a new method called PEEU to improve the task planning capabilities of small, open-source multimodal web agents that assist humans in operating repetitive graphical user interface (GUI) tasks…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification can have vulnerabilities missed during standard evaluation because they learn token-level indicator semantics that work well on their…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification may overlook vulnerabilities introduced during fine-tuning itself. These models can learn token-level indicator semantics that preserve…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) of large language models (LLMs). The benchmark includes step-wise causal annotations for LLMs and addresses the issue that existing…
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
The paper proposes a new method called Reasoning-guided progressive Open Relation Extraction (ReaORE) to improve the performance of Open Relation Extraction (OpenRE). This method addresses the limitations of current…
Semantic Early-Stopping for Iterative LLM Agent Loops
The research presents a method called semantic early-stopping for multi-agent large language model (LLM) loops, such as a Writer and a Critic. The goal is to halt the loop when the consecutive draft embeddings no…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
The paper presents GAversary, a new method for generating adversarial attacks on natural language models using a Genetic Algorithm (GA). This method is able to reduce the accuracy of several target models significantly…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Researchers have developed a new method called GAversary, which uses a Genetic Algorithm (GA) and GloVe embeddings to generate adversarial attacks on natural language models. These attacks can significantly reduce the…
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
The study examines the use of multiple language models (LLMs) to improve accuracy over single models and finds that their performance is limited by a factor called 'beta'. Beta represents the rate at which all models…
Autodata: An agentic data scientist to create high quality synthetic data
Researchers introduce Autodata, an AI agent that can act as a data scientist to create high-quality synthetic data for various tasks like computer science research, legal reasoning, and mathematical object reasoning…
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
The research introduces FORCE, a three-stage framework for fine-tuning Vision-Language-Action (VLA) models using Reinforcement Learning (RL). The framework addresses sample inefficiency issues by implementing a…
GUI agent: Guided Exploration of User-Sensitive Screens
This research presents a new agent called Guided Exploration of User-Sensitive Screens (GUI agent) designed to automate tasks within an open Graphical User Interface (GUI) environment. The GUI agent is intended to…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
The paper introduces Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method for inferring which agents are working together and what each…
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Researchers present a new method called 'progress advantage' for evaluating Language Learning Models (LLMs) without the need for dedicated reward model training. This method is based on reinforcement learning (RL)…
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
The paper discusses a method called On-policy Self-Distillation, which uses a single model as both teacher and student to achieve high accuracy in pass@1. However, it is found that this method can lead to a decrease in…
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Researchers have proposed a framework called SARA (Semantically Anchored Routing Alignment) to improve the performance of multilingual language models in low-resource languages. The framework aligns the routing…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
