440900 results (page 10 of 17636)
-
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods rely on explicit edge traversal, making them fragile to KG incompleteness. In this paper, we proposed …
-
SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker
Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets, which fundamentally erodes PEFT's efficiency promise. In this work, we introduce SEATrack, a Simple, Efficient, and Adaptive two-stream multimodal tracker that tackles this performance-efficiency dilemma from two compl…
-
Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design
Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the conditions under which this occurs remain unclear. We train 11 instruction-tuned LLMs (0.5B--14B) with on-policy RL across 3 environments and find that model size acts as a safety buffer in some environments but enables greater harmful exploitation in o…
-
Lit2Vec: A Reproducible Workflow for Building a Legally Screened Chemistry Corpus from S2ORC for Downstream Retrieval and Text Mining
We present Lit2Vec, a reproducible workflow for constructing and validating a chemistry corpus from the Semantic Scholar Open Research Corpus using conservative, metadata-based license screening. Using this workflow, we assembled an internal study corpus of 582,683 chemistry-specific full-text research articles with structured full text, token-aware paragraph chunks, paragraph-level embeddings gen…
-
Adaptive Budget Allocation in LLM-Augmented Surveys
Large language models (LLMs) can generate survey responses at low cost, but their reliability varies substantially across questions and is unknown before data collection. Deploying LLMs in surveys still requires costly human responses for verification and correction. How should a limited human-labeling budget be allocated across questions in real time? We propose an adaptive allocation algorithm t…
-
Multiwavelength Study of Blue Straggler Stars in Tombaugh 2: Evidence for Binary Mass Transfer and Constraints on Cluster Dynamical State
We present a focused multiwavelength study of blue straggler stars (BSSs) in the intermediate-age open cluster Tombaugh 2, located in the outer Galactic disk, to constrain the dominant formation pathways of BSSs in a low-density environment. Cluster members are identified using Gaia DR3 astrometry through a Gaussian Mixture Model, yielding a clean sample of high-probability members. Color-magnitud…
-
Latent Planning Emerges with Scale
LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however, the extent to which they implicitly plan is unknown. In this paper, we define latent planning as occurring when LLMs possess internal planning representations that (1) cause the generation of a specific future token or concept, and (2) shape preced…
-
Calibrated Confidence Estimation for Tabular Question Answering
Large language models (LLMs) are increasingly deployed for tabular question answering, yet calibration on structured data is largely unstudied. This paper presents the first systematic comparison of five confidence estimation methods across five frontier LLMs and two tabular QA benchmarks. All models are severely overconfident (smooth ECE 0.35-0.64 versus 0.10-0.15 reported for textual Q…
-
Deepfakes at Face Value: Image and Authority
Deepfakes are synthetic media that superimpose or generate someone's likeness on to pre-existing sound, images, or videos using deep learning methods. Existing accounts of the wrongs involved in creating and distributing deepfakes focus on the harms they cause or the non-normative interests they violate. However, these approaches do not explain how deepfakes can be wrongful even when they cause no…
-
KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive reasoning. Structured Knowledge Graphs (KGs) provide an effective form of external knowledge representation and have been widely used to enhance performance in classical Knowledge Base Question Answering (KBQA) tasks. However, performing precise multi-h…
-
DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation
Long-horizon collaborative vision-language navigation (VLN) is critical for multi-robot systems to accomplish complex tasks beyond the capability of a single agent. CoNavBench takes a first step by introducing the first collaborative long-horizon VLN benchmark with relay-style multi-robot tasks, a collaboration taxonomy, along with graph-grounded generation and evaluation to model handoffs and ren…
-
Elastic Net Regularization and Gabor Dictionary for Classification of Heart Sound Signals using Deep Learning
In this article, we propose the optimization of the resolution of time-frequency atoms and the regularization of fitting models to obtain better representations of heart sound signals. This is done by evaluating the classification performance of deep learning (DL) networks in discriminating five heart valvular conditions based on a new class of time-frequency feature matrices derived from the fitt…
-
Social Learning Strategies for Evolved Virtual Soft Robots
Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control parameters influence how well the morphology performs. This joint optimization can be done through nested loops of evolutionary and learning processes, where the control parameters of each robot are learned independently. However, the control parameter…
-
T2I-BiasBench: A Multi-Metric Framework for Auditing Demographic and Cultural Bias in Text-to-Image Models
Text-to-image (T2I) generative models achieve impressive visual fidelity but inherit and amplify demographic imbalances and cultural biases embedded in training data. We introduce T2I-BiasBench, a unified evaluation framework of thirteen complementary metrics that jointly captures demographic bias, element omission, and cultural collapse in diffusion models - the first framework to address all thr…
-
Audio Source Separation in Reverberant Environments using $β$-divergence based Nonnegative Factorization
In Gaussian model-based multichannel audio source separation, the likelihood of observed mixtures of source signals is parametrized by source spectral variances and by associated spatial covariance matrices. These parameters are estimated by maximizing the likelihood through an Expectation-Maximization algorithm and used to separate the signals by means of multichannel Wiener filtering. We propo…
-
Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning
Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving ind…
-
Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe
Large language models (LLMs) are trained on data contributed by low-resource language communities, yet the linguistic knowledge encoded in these models remains accessible only through commercial APIs. This paper investigates whether strategic prompting can extract usable text data from LLMs for two West African languages: Hausa (Afroasiatic, approximately 80 million speakers) and Fongbe (Niger-Con…
-
From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution
In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission. Such problems are inherently mixed discrete-continuous: a high-level action sequence and a physically feasible continuous trajectory. The resulting trajectory and action sequence must also satisfy problem constraints such as deadlines, time windows, and velocity or acceleration limits. While hybrid tem…
-
Designing for Error Recovery in Human-Robot Interaction
This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the performance of one individual system to beyond so-called human baselines. However, these systems often look at one shot and one-way decisions, whereas the real world is more continuous and interactive. Humans, however, are often able to recover from …
-
Beyond Single-Dimension Novelty: How Combinations of Theory, Method, and Results-based Novelty Shape Scientific Impact
Scientific novelty drives advances at the research frontier, yet it is also associated with heightened uncertainty and potential resistance from incumbent paradigms, leading to complex patterns of scientific impact. Prior studies have primarily ex-amined the relationship between a single dimension of novelty -- such as theoreti-cal, methodological, or results-based novelty -- and scientific impact…
-
Intelligent ROI-Based Vehicle Counting Framework for Automated Traffic Monitoring
Accurate vehicle counting through video surveillance is crucial for efficient traffic management. However, achieving high counting accuracy while ensuring computational efficiency remains a challenge. To address this, we propose a fully automated, video-based vehicle counting framework designed to optimize both computational efficiency and counting accuracy. Our framework operates in two distinct …
-
Analyzing the Effect of Noise in LLM Fine-tuning
Fine-tuning is the dominant paradigm for adapting pretrained large language models (LLMs) to downstream NLP tasks. In practice, fine-tuning datasets may contain various forms of noise arising from annotation errors, preprocessing artifacts, or automated data collection. While prior work has focused on designing robust learning algorithms to mitigate performance degradation under noisy conditions, …
-
Euler-inspired Decoupling Neural Operator for Efficient Pansharpening
Pansharpening aims to synthesize high-resolution multispectral (HR-MS) images by fusing the spatial textures of panchromatic (PAN) images with the spectral information of low-resolution multispectral (LR-MS) images. While recent deep learning paradigms, especially diffusion-based operators, have pushed the performance boundaries, they often encounter spectral-spatial blurring and prohibitive compu…
-
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred un…
-
Enhancing Clustering: An Explainable Approach via Filtered Patterns
Machine learning has become a central research area, with increasing attention devoted to explainable clustering, also known as conceptual clustering, which is a knowledge-driven unsupervised learning paradigm that partitions data into $θ$ disjoint clusters, where each cluster is described by an explicit symbolic representation, typically expressed as a closed pattern or itemset. By providing huma…