Large Language Models

Security in LLM-as-a-Judge: A Comprehensive SoK

Hallucination-aware intermediate representation edit in large vision-language models

AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models

Adversarial Prompt Injection Attack on Multimodal Large Language Models

Few-shot Writer Adaptation via Multimodal In-Context Learning

An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms

M-MiniGPT4: Multilingual VLLM Alignment via Translated Data

MemFactory: Unified Inference & Training Framework for Agent Memory

Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metrics

Baby Scale: Investigating Models Trained on Individual Children's Language Input

Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models

Convergent Representations of Linguistic Constructions in Human and Artificial Neural Systems

Concept frustration: Aligning human concepts and machine representations

Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models

Mind the Gap: A Framework for Assessing Pitfalls in Multimodal Active Learning

KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models

BotVerse: Real-Time Event-Driven Simulation of Social Agents

From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

GENIE: Gram-Eigenmode INR Editing with Closed-Form Geometry Updates

Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation

Generative AI in Action: Field Experimental Evidence from Alibaba's Customer Service Operations

Interview-Informed Generative Agents for Product Discovery: A Validation Study

UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates

Bethe Ansatz with a Large Language Model

Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives

Hybrid Framework for Robotic Manipulation: Integrating Reinforcement Learning and Large Language Models

Tucker Attention: A generalization of approximate attention mechanisms

Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?

MindCube: Spatial Mental Modeling from Limited Views

CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models

MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support

Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models

Distilling LLM Reasoning into Graph of Concept Predictors

GenOL: Generating Diverse Examples for Name-only Online Learning

SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy

EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context

We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback

Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation

LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression

FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles

Denoising the Future: Top-p Distributions for Moving Through Time

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms