All notes, newest first
2,343 notes. Notes 1,001 to 1,050, page 21 of 47.
Co-Evolving LLM Evaluators and Policies via DynamicRubric
The paper introduces DynamicRubric, a framework that co-evolves language model evaluators and policies by generating weighted binary rubrics for each candidate set and aggregating the resulting judgments into…
Co-Evolving LLM Evaluators and Policies via DynamicRubric
The researchers propose DynamicRubric, a method that allows large language models to improve by co-evolving evaluators and policies. This method generates weighted binary rubrics for each candidate set and aggregates…
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
The paper introduces Cumsum-Composable Phase Transport, a new streaming-native temporal layer for keyword spotting in speech tasks. This method uses unitary rotations to project and transport acoustic frames…
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
A research paper introduces Cumsum-Composable Phase Transport, a new temporal layer designed for keyword spotting in streaming speech. This method projects acoustic frames to complex channels, transports them using…
CURED: Creating, Understanding, and Repairing Errors Demonstrator
The paper presents CURED, a web application that allows users to upload tabular data, introduce errors, and use machine learning methods to clean and understand the error mechanisms in the data. The goal is to bridge…
Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions
The authors propose a method for decentralized online optimization on Riemannian manifolds with strongly geodesically convex (strongly g-convex) losses, improving upon existing methods that only address g-convex…
Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions
The authors study decentralized online optimization for specific types of functions (strongly geodesically convex) on Riemannian manifolds with certain curvature properties. They propose a new network-error analysis to…
ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers
Researchers propose ELSAA, a method to approximate attention in Transformers more efficiently by using sparse and low-rank branches instead of calculating the full quadratic score matrix. This is done to handle longer…
Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment
Researchers evaluate the bias in pre-trained language models used for AI-based recruitment systems, focusing on gender leakage from CV data. They analyze nine models using a synthetic dataset and a multi-task…
Generalized Kalman filter based temporal difference reinforcement learning
The paper introduces a new reinforcement learning framework that combines conditional expectation theory with a generalized Kalman filter. This approach allows for the estimation of both the value function and its…
Hard Guarantees at a Measured Price: Entropy-Stable Learned Finite Volumes for Compressible Flow
The author presents a new learned finite volume scheme for two-dimensional compressible flow that guarantees physical admissibility by construction and has an entropy-stable interior flux. The scheme was evaluated…
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
Researchers propose HeadCast, a framework that improves the efficiency of autoregressive video diffusion models without requiring re-training. The framework categorizes attention heads into four types based on their…
HijackKV: New Threat in Position-Independent KV Cache Reuse
Researchers have identified a new threat called KV Cache Hijacking in position-independent KV cache reuse, which is used to reduce inference latency in large language models. This threat allows an attacker to silently…
Instance Hardness-Based Relevance for Imbalanced Regression
A new approach called Instance Hardness-based relevance function (InHaR) is proposed to identify rare instances in regression problems, particularly useful for complex scenarios like bimodal distributions where…
Instance Hardness-Based Relevance for Imbalanced Regression
The paper proposes a new relevance function called Instance Hardness-based relevance (InHaR) for identifying rare instances in imbalanced regression problems. This function takes into account the learning difficulty of…
Interpretable Fuzzy Rule-Based Regression Extension for Ex-Fuzzy Library
Researchers present an extension for the Ex-Fuzzy library that makes Mamdani-style fuzzy regression more accessible in modern machine learning software. This extension allows for learning from data and offers…
Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields
Researchers propose a new method to train Attention Graph Neural Networks for predicting three-dimensional thermo-fluid fields. Instead of using conventional numerical solvers that incur high computational costs, they…
Lipschitzian SLLNs for random functions
The authors present a new Strong Law of Large Numbers (SLLN) for locally Lipschitz functions in the context of the Lipschitz pseudometric. The SLLNs hold under either a topological or model-theoretic condition, and can…
Local Stability and Gaussian Smoothing of Quantized Neural Networks
The authors investigate using Gaussian averaging as a smooth alternative for quantized neural networks. They provide bounds on the difference between the original function (f) and the smoothed version (g), linking it…
Local Stability and Gaussian Smoothing of Quantized Neural Networks
The authors study the use of Gaussian averaging as a smoother alternative for quantized neural networks. They derive a bound on the difference between the original function and the smoothed version under certain…
Multi-modal transformer for signal classification in nanopore blockade experiments
Researchers present a deep learning architecture for analyzing complex signals from nanopore blockade experiments. The model, which combines multiple signal representations, outperforms existing methods on a peptide…
Multi-stage Dynamic Selection for Cross-Project Defect Prediction
The paper proposes a new framework for Cross-Project Defect Prediction (CPDP) that addresses distribution shift issues between training and target projects by using a two-stage multiple classifier system selection…
Non--negative matrix factorization using the extit{R} package extsf{nnmf}
This research presents a new R package for Non-negative Matrix Factorization (NMF) and compares it with two other widely used NMF packages in R. The comparison is based on real-world data instead of simulated datasets…
Non--negative matrix factorization using the extit{R} package extsf{nnmf}
The paper introduces a new R package for Non-negative Matrix Factorization (NMF) and compares its performance with two other widely used NMF packages in R. Instead of using simulated data, the comparison is based on…
OLEDLM: A Unified Language Model for OLED Molecular Design
Researchers propose a unified language model named OLEDLM for the design of OLED materials. The model directly generates OLED molecular structures that meet specified optoelectronic properties, using a multi-stage…
OLEDLM: A Unified Language Model for OLED Molecular Design
Researchers propose a new language model for designing Organic Light-Emitting Diode (OLED) materials. The model generates SMILES sequences of OLED molecules based on specific optoelectronic properties, using a…
On Optimization Complexity of Second-Order Certified Unlearning
The authors investigate the complexity of removing trained data from machine learning models, focusing on certified unlearning and optimization accuracy. They propose new bounds on the distance between initial and…
On Optimization Complexity of Second-Order Certified Unlearning
The authors study the complexity of removing memorized training data from a machine learning model while maintaining accuracy, a process known as certified unlearning. They present new bounds on the distance between…
PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring
The study introduces PhaseAware, a framework designed for continuous evaluation of rehabilitation quality during physical therapy sessions. It combines temporal data with phase-specific and body part descriptors to…
PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling
The researchers propose Physics-Informed Environmental Retrieval (PIER), a model-agnostic framework to improve the accuracy of environmental system modeling. The framework is designed to address challenges in limited…
Plausibility-Driven Prioritization of Candidate Biomedical Annotations
The paper presents a framework using biomedical knowledge graphs (bioKGs) to estimate the plausibility of candidate biomedical annotations, aiming to guide experts in prioritizing them for manual curation. The approach…
Statistical Inference for Rank Allocation in Low-Rank Adaptation
In this paper, the authors propose StatLoRA, a statistical inference-based rank allocation method for low-rank adaptation (LoRA) in large language models. The proposed method uses estimated p-values to determine which…
Statistical Inference for Rank Allocation in Low-Rank Adaptation
Researchers propose StatLoRA, a statistical inference-based method for rank allocation in low-rank adaptation (LoRA). This method aims to balance efficiency, expressiveness, and generalization by using estimated…
Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection
Researchers have developed an energy-efficient method for Android malware detection using deep learning models, aiming to balance performance and battery life. They used quantized neural networks (QNNs) with reduced…
Test Case Prioritization for DNNs via Neural Collapse Instability
A new method, Neural-Collapse-Inspired Prioritization (NCIP), is proposed to improve test case prioritization for deep neural networks (DNNs) in safety-critical domains where testing budgets are limited. The method…
The Blessing of Dimensionality: How Near-Orthogonality in High-Dimensional Spaces Explains Temporal Portability
The paper addresses two open questions regarding a method called PortLLM, which adapts large language models after continual pretraining. The authors perform an extensive empirical study to explore the long-term…
Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models
This study evaluates various AI/ML models for forecasting bandwidth utilization in networks, aiming to improve capacity planning and reduce costly over-provisioning.
Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning
The paper describes a new control stack for miniature humanoids that allows a single operator to see, manipulate, and navigate in distant environments using Virtual Reality (VR) for upper-body teleoperation and…
Variance-reduced Domain Adaptation using Paired Sampling
The paper proposes Paired Sampling for Domain Adaptation (PSDA), a new stochastic variance reduction technique designed for distribution-matching frameworks in unsupervised domain adaptation (UDA) that suffer from high…
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
AgentDebugX is an open-source toolkit designed to aid in the observation, identification of root causes, recovery, and rerunning of issues in LLM (Large Language Model) agents. The toolkit, DeepDebug, uses multi-turn…
Agents in the Wild: Where Research Meets Deployment
This tutorial paper discusses the transition of large language model (LLM) based agentic systems from research to practical use in various fields like software engineering, scientific discovery, and finance. It…
AI Tour Meeting: Group Travel Planning by LLM Agents
This research presents AI Tour Meeting, a group travel planning system that uses multiple Large Language Model (LLM) agents with distinct personas to collaboratively create an itinerary based on their constraints and…
AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System
The paper introduces AILQA, an AI system designed for Indian legal question answering, using a variety of embedding and generative models including LLMs. It was evaluated with both lexical and semantic metrics, expert…
AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism
The researchers present AutoJourn, a system for generating news articles using large language models (LLMs) that consider multiple perspectives and aim to reduce bias in AI-generated news. The system includes…
Automated Extraction of Techno-Economic Data from 76,000 Energy System Studies
Researchers developed a method to automatically extract quantitative information from 76,000 energy system studies published since 2010. They compiled over 3 million structured data points and 20 million metadata…
Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
A research paper proposes using bounding boxes to improve the accuracy and efficiency of Small Language Models (SLMs) when grading handwritten student exams. The study finds that this method significantly enhances…
CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
Researchers propose a new framework called CASE to improve the faithfulness of chain-of-thought (CoT) reasoning in large language models (LLMs). The goal is to ensure that the generated reasoning supports the final…
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
The paper provides a survey on computational humor, focusing on visual humor in memes, cartoons, and comics. The study outlines the challenges faced by AI systems in understanding and generating such humor due to…
Computing on the Fly: Navigating a Vision for the Future of Drone Computing
The report discusses the potential future use of drones for delivering goods, medical supplies, and information on a scale similar to national infrastructure investments like highways and the electric grid. However, it…
DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning
The paper introduces Dependency-Aware Intermediate QA Supervision (DAIS), a framework that improves the accuracy of answering complex questions by providing intermediate rationales and conditioning local answers on…
Page 21 of 47
