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.
84 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on natural language processing
84 notes, page 3 of 4
Evidence-Backed Video Question Answering
The authors propose Evidence-Backed Video Question Answering (E-VQA), a new task that requires models to not only provide answers but also the specific spatial and temporal evidence from videos. They introduce…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient in-training low-rank regularization framework for neural networks. It aims to improve compressibility without significant accuracy loss, while avoiding the limitations…
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
UltraX is a new framework designed to improve the quality of large-scale pre-training data for Large Language Models (LLMs). It addresses the limitations of existing methods by offering fine-grained instance-level…
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Researchers have developed a method called SynthAVE to generate large amounts of labeled data for e-commerce attribute extraction using synthetic labels validated by multiple large language models (LLMs). The benchmark…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
The paper proposes ARGTCA, a method to improve the calibration of Vision-Language Models (VLMs) by using Graph Attention Networks to capture inter-attribute dependencies and reduce overconfidence during test-time…
Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
The paper introduces DataGovBench, a benchmark for evaluating the performance of Large Language Models (LLMs) in practical scenarios, such as complex data analysis and insight discovery from large multi-tabular…
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
The research introduces DepthWeave-KV, a new cache compression method for long-context language models. This method adapts to the needs of different tokens by factorizing key and value states across neighboring…
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
The paper introduces FreqDepthKV, an inference-time cache compression method for long-context LLM (Large Language Model) inference that reduces memory and bandwidth costs while maintaining task accuracy on various…
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications
The author introduces RuBench 1.0, a benchmark for evaluating coding agents that use native language tasks instead of English. The benchmark includes 25 tasks mined from five open-source repositories and is judged by…
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
The researchers have developed a multi-agent framework called OptiAgent that can take a natural language description of an Operations Research problem and produce a mathematically formulated solution along with…
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
A new benchmark called SPEARBench is introduced to evaluate the naturalness of speech-to-speech language models during question-answer interactions. The benchmark covers aspects like response latency, interruptions…
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
The paper proposes a new method called Neuron On-Policy Self-Distillation (Neuron-OPSD) for annotation-free self-distillation of large language models. This method uses the internal neuron activations to guide data…
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
The text introduces 'adversarial pragmatics', a new benchmark and annotation protocol to evaluate the behavior of language models in various ambiguous situations. The goal is to clarify whether failures occur due to…
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
The paper introduces Adversarial Pragmatics, a benchmark and annotation protocol for evaluating language models' behavior in situations of instruction conflict, embedded commands, and policy ambiguity. The benchmark is…
Freeform Preference Learning for Robotic Manipulation
Researchers introduce Freeform Preference Learning (FPL), a method for training robotic policies based on natural-language preferences provided by humans, rather than binary labels. The method uses the preferences to…
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
The research paper introduces MECoBench, a benchmark for evaluating the collaboration abilities of multimodal agents in visually grounded environments. The study explores three key findings: collaboration generally…
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
The researchers have developed a framework called PolicyGuard to ensure documents comply with an organization's specific policies or guidelines. Instead of relying on large language models for end-to-end prompting…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers have proposed a multi-agent system that uses expert decision trees and Vision-Language Models (VLMs) to automate the bias classification in tree height in forestry remote sensing. The system mitigates VLM…
Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval
Researchers propose a method called permutation-invariant fine-tuning (PI-FT) to improve structured metadata retrieval. They show that the choice of field order in a record can significantly impact retrieval quality…
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…
TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
Researchers introduce a dataset (DyadEE) for studying emotional entrainment in dyadic speech interactions, including both entrained and disrupted conversations. They also propose TRACE, a new framework that models…
Translating Natural Language to Strategic Temporal Specifications via LLMs
Researchers have developed a framework for translating Natural Language descriptions of strategic requirements into well-formed ATL/ATL* formulas using Large Language Models (LLMs). They created and validated a novel…
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…
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.
