Research
Research
Research
Research
189+ open-access research outputs.
Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on lon…
Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. H…
Deploying large language models to heterogeneous hardware is often constrained by memory, not compute. We introduce MCAP (Monte Carlo Activation Profiling), a load-time per-layer importance estimator …
Story Visualization aims to generate a sequence of images that faithfully depicts a textual narrative that preserve character identity, spatial configuration, and stylistic coherence as the narratives…
Image captioning for Early Childhood Education (ECE) is essential for automated activity understanding and educational assessment. However, existing methods face two key challenges. First, the lack of…
Autonomous trucking poses unique challenges due to articulated tractor-trailer geometry, and time-varying sensor poses caused by the fifth-wheel joint and trailer flex. Existing perception and calibra…
Multi-RF Fusion achieves a test ROC-AUC of 0.8476 +/- 0.0002 on ogbg-molhiv (10 seeds), placing #1 on the OGB leaderboard ahead of HyperFusion (0.8475 +/- 0.0003). The core of the method is a rank-ave…
Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions. Current large language model (LLM)-based conversational agents lac…
Tabular data is the primary data format in industrial relational databases, underpinning modern data analytics and decision-making. However, the increasing scale of tabular data poses significant comp…
Robust perception in brains is often attributed to high-dimensional population activity together with local plasticity mechanisms that reinforce recurring structure. In contrast, most modern image rec…
Spoken code-switching (CSW) challenges syntactic parsing in ways not observed in written text. Disfluencies, repetition, ellipsis, and discourse-driven structure routinely violate standard Universal D…
Conformal prediction, a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under the assumption of data exchangeability. Unfortunate…
Fine-Tuning-as-a-Service (FTaaS) facilitates the customization of Multimodal Large Language Models (MLLMs) but introduces critical backdoor risks via poisoned data. Existing defenses either rely on su…
Imputing missing node features in graphs is challenging, particularly under high missing rates. Existing methods based on latent representations or global diffusion often fail to produce reliable esti…
Recognizing and navigating client resistance is critical for effective mental health counseling, yet detecting such behaviors is particularly challenging in text-based interactions. Existing NLP appro…
In this paper, we propose active recap learning (ARL), a framework for enhancing large language model (LLM) in understanding long contexts. ARL enables models to revisit and summarize earlier content …
The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alig…
This paper proposes a Dialect Identification (DID) approach inspired by the Connectionist Temporal Classification (CTC) loss function as used in Automatic Speech Recognition (ASR). CTC-DID frames the …
Prompt-based methods, which encode medical priors through descriptive text, have been only minimally explored for CT Image Quality Assessment (IQA). While such prompts can embed prior knowledge about …
Emotional states manifest as coordinated yet heterogeneous physiological responses across central and autonomic systems, posing a fundamental challenge for multimodal representation learning in affect…
Free open-access publishing with Google Scholar indexing.
Submission Guide →