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 5 of 10
RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
The paper introduces RAGAL, a locally-hosted AI assistant developed for a Romanian agency's technical support team. The system was designed to function within strict data locality constraints, with no external API…
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
The authors propose a method to improve the accuracy of automatic speech recognition (ASR) models by controlling the activation of 'verbatim' versus 'intended' transcription styles. They argue that current models…
Automated Discovery Has No Universally Superior Harness
A study investigates the effectiveness of different automated discovery systems (OpenEvolve and TTT-Discover) in various machine learning models and problems. The research finds that no single system consistently…
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Researchers propose a new method called SOPHIA for controlling the reasoning process of large language models, which are currently uncontrollable despite their extended use. The proposed method involves treating each…
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
The paper proposes a framework called Exploratory-Assimilating Reflection (EAR) for autonomous agents with limited context window and external memory. EAR aims to improve retrieval performance by combining two…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
The paper introduces MADA-RL, a method for fine-tuning compact language models with limited budgets. It specializes the models into generator and critic roles and trains them using a debate-aware learning signal. The…
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Researchers have developed a new method for Industrial Video Anomaly Detection (IVAD) that aims to identify unusual objects and events in industrial processes. This method is designed to work in complex settings where…
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
Researchers propose a simple method to merge large language models with significantly different parameters without training or alignment by using dimensional adaptation and ratio-controlled interpolation. The method…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
Researchers have proposed a new tool called Symbolic Geometric Agent (SGA) to improve the spatial correctness and visual legibility of educational videos generated by Large Language Models (LLMs). The SGA intercepts…
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
Researchers propose SIEVE, a framework for detecting video misinformation by first identifying key pieces of evidence that contribute to the decision, and then verifying the veracity based on these identified pieces…
Stress Testing Concept Erasure with Large Language Model Agents
The paper introduces a new framework called Stress Testing Agents for Concept Erasure (STACE). STACE uses multiple Large Language Model (LLM) agents to stress-test models that have had certain concepts erased from…
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
The authors show that fine-tuning language models on specific datasets can cause broad shifts in ideology across various topics, even when the training data is factually defensible and moderation-passing. This…
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
Researchers show that fine-tuning language models on specific policies or domains can cause broad ideological shifts across various topics, even when the data used is factually defensible and moderation-passing. This…
Latent Trajectory Discrimination for AI-Generated Text Detection
The paper presents a new approach for detecting AI-generated text called Geometric Trajectory and Contrastive Learning (GTCL). Instead of treating documents as static objects, GTCL models how textual representations…
Latent Trajectory Discrimination for AI-Generated Text Detection
In this paper, the authors propose a new approach for detecting AI-generated text called Geometric Trajectory and Contrastive Learning (GTCL). Unlike existing methods that focus on aggregate statistics or global…
Long-Context Fine-Tuning with Limited VRAM
Researchers introduce Hierarchical Global Attention (HGA) to reduce memory usage during long training sequences in large language models. They use segment-wise backpropagation, tiered KV storage, and detach older data…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have created a new benchmark called MM-IssueLoc to evaluate the effectiveness of multimodal repository-level issue localization, which includes visual evidence such as screenshots and logs. Current…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have introduced a new benchmark called MM-IssueLoc for evaluating the effectiveness of systems in repository-level issue localization that also includes visual evidence such as screenshots, error dialogs…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers introduce MM-IssueLoc, a benchmark and evaluation protocol designed specifically for repository-level issue localization with visual evidence. The dataset includes 652 issue-PR instances across multiple…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization that includes visual evidence. The benchmark has 652 issue-PR instances across 23 languages with annotations…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a new benchmark and evaluation protocol for repository-level issue localization with visual evidence. The benchmark contains over 650 issue-PR instances across multiple languages…
Scaling Behavior Foundation Model for Humanoid Robots
Researchers propose a scaling recipe for Behavior Foundation Models (BFMs) to improve the capabilities of humanoid robots. The recipe includes a learning paradigm, strategic synergy between data collection methods, and…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
Researchers propose a graph neural network approach to detect and analyze reasoning structures in large language models (LLMs) generated texts for improved robustness against paraphrasing and obfuscation techniques…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
The paper proposes a new method for detecting text generated by large language models (LLMs) and attributing authorship to them. The method goes beyond just analyzing surface-level linguistic features and instead…
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.
