Large Language Models

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

Incorporating LLM Embeddings for Variation Across the Human Genome

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks

Align Your Query: Representation Alignment for Multimodality Medical Object Detection

Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling

REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis

TransFIRA: Transfer Learning for Face Image Recognizability Assessment

A Semi-amortized Lifted Learning-to-Optimize Masked (SALLO-M) Transformer Model for Scalable and Generalizable Beamforming

ShishuLM : Achieving Optimal and Efficient Parameterization with Low Attention Transformer Models

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

Stronger Normalization-Free Transformers

Evaluation of Generative Models for Emotional 3D Animation Generation in VR

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models

The Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation

PAIR-Former: Budgeted Relational MIL for miRNA Target Prediction

$V_0$: A Generalist Value Model for Any Policy at State Zero

How to Train Your Long-Context Visual Document Model

Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models

DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

Evidential Neural Radiance Fields

When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation

Training for Technology: Adoption and Productive Use of Generative AI in Legal Analysis

When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On

Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting

How do LLMs Compute Verbal Confidence

I Read All 512,000 Lines of Claude Code's Leaked Source — Here's What Anthropic Was Hiding

What is OpenClaw? Your AI Agent in the Machine

AI Weekly: 3/27–4/1 | Anthropic's Triple Shock, Arm's First-Ever Chip, Apple Opens Siri to Rivals

Beyond the Hype: Building AI Agents That Actually Remember

Big Tech firms are accelerating AI investments and integration, while regulators and companies focus on safety and responsible adoption.

Platform Consolidation Meets Macro Recession Pricing — March 31, 2026

Prompt Engineering for Senior Devs: Scaling Excellence Without Technical Debt

SpyderBot Earns a 96.53 Proof of Usefulness Score by Building Real-Time GEO Analytics to Track LLM Mentions

Accent Labs Earns a 53.73 Proof of Usefulness Score by Building Critical Data Infrastructure for African Voice AI

Multimodal Embeddings and RAG: A Practical Guide