An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models
arXiv:2602.20324v1 Announce Type: new
Abstract: Phenotyping is fundamental to rare disease diagnosis, but manual curation of structured phenotypes from clinical notes is labor-intensive and difficult to scale. Existing artificial intelligence approaches typically optimize individual components of p...
DMCD: Semantic-Statistical Framework for Causal Discovery
arXiv:2602.20333v1 Announce Type: new
Abstract: We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model proposes a spar...
Diffusion Modulation via Environment Mechanism Modeling for Planning
arXiv:2602.20422v1 Announce Type: new
Abstract: Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating trajectories in ...
Implicit Intelligence -- Evaluating Agents on What Users Don't Say
arXiv:2602.20424v1 Announce Type: new
Abstract: Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit instruction-following bu...
Closing the Gap Between Text and Speech Understanding in LLMs
Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counterparts—and even cascaded pipelines—on language understanding tasks. We term this shortfall the text-speech understanding...
A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning
Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting material recovery. We present A.R.I.S. (Automated Recycling Identification System), a low-cost, portable sorter for shredded e-waste that a...
Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance improvement through fine-tuning often results from the strengthening ...
Reusing Pre-Training Data at Test Time is a Compute Multiplier
Large language models learn from their vast pre-training corpora, gaining the ability to solve an ever increasing variety of tasks; yet although researchers work to improve these datasets, there is little effort to understand how efficient the pre-training apparatus is at extracting ideas and knowle...
Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling
arXiv:2602.18472v1 Announce Type: new
Abstract: Physiologically Based Pharmacokinetic (PBPK) modeling is a cornerstone of model-informed drug development (MIDD), providing a mechanistic framework to predict drug absorption, distribution, metabolism, and excretion (ADME). Despite its utility, adopti...
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
arXiv:2602.18493v1 Announce Type: new
Abstract: Long-context LLMs and Retrieval-Augmented Generation (RAG) systems process information passively, deferring state tracking, contradiction resolution, and evidence aggregation to query time, which becomes brittle under ultra long streams with frequent ...
Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications
arXiv:2602.18582v1 Announce Type: new
Abstract: When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifi...
Feedback-based Automated Verification in Vibe Coding of CAS Adaptation Built on Constraint Logic
arXiv:2602.18607v1 Announce Type: new
Abstract: In CAS adaptation, a challenge is to define the dynamic architecture of the system and changes in its behavior. Implementation-wise, this is projected into an adaptation mechanism, typically realized as an Adaptation Manager (AM). With the advances of...
Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System
arXiv:2602.18640v1 Announce Type: new
Abstract: Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context constraint...
arXiv:2602.18671v1 Announce Type: new
Abstract: We reinterpret the final Large Language Model (LLM) softmax classifier as an Energy-Based Model (EBM), decomposing the sequence-to-sequence probability chain into multiple interacting EBMs at inference. This principled approach allows us to track "ene...
The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to human-like reasoning is undeniable, the driving forces underpinni...
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining
One of the first pre-processing steps for constructing web-scale LLM pretraining datasets involves extracting text from HTML. Despite the immense diversity of web content, existing open-source datasets predominantly apply a single fixed extractor to all webpages. In this work, we investigate whether...
AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and grounding events across time. These scenarios are central to multimo...
Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving
arXiv:2602.17677v1 Announce Type: new
Abstract: Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly susceptible...
Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization
arXiv:2602.17679v1 Announce Type: new
Abstract: Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing with high-dimensional multi-stage systems, where we can observe intermediate outputs. Standard BO model...
BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
arXiv:2602.17680v1 Announce Type: new
Abstract: Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to inter...
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
arXiv:2602.17681v1 Announce Type: new
Abstract: Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly improve quantizat...
Duality Models: An Embarrassingly Simple One-step Generation Paradigm
arXiv:2602.17682v1 Announce Type: new
Abstract: Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to mo...
Epistemic Traps: Rational Misalignment Driven by Model Misspecification
arXiv:2602.17676v1 Announce Type: new
Abstract: The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation via reinfor...