DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic re...
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the “one-to-many” nature of video description, where high-quality captions are oft...
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like ...
7 signs your AI infrastructure is still stuck in the HPC era
Your GPU dashboard can look perfectly healthy while doing almost no useful work, and most enterprises are staring at exactly that chart right now. The real bottleneck rarely lives in the silicon. It lives in the storage, pipelines, and scheduler...
AhaBench: Do Agents Learn from Prior Experience? A Benchmark for Long-Horizon Continual Learning
arXiv:2609.05435v1 Announce Type: new
Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt to delayed consequences. Most evaluations still reset the agent after a prompt or score only the fi...
Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
arXiv:2609.05575v1 Announce Type: new
Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability, essential both for the science of deep learning and for the trustworthy deployment of increasingly ...
HB-PVI: A Hierarchical Bayesian Personalization and Value-of-Information Framework for Complex Activity Recognition
arXiv:2609.05582v1 Announce Type: new
Abstract: Personalization can improve activity-recognition performance, but participant-specific gains are heterogeneous, and every additional calibration label has an acquisition cost. This study presents HB-PVI, a hierarchical Bayesian personalization and val...
Adaptive Entangled Game Modules in Artificial General Intelligence
arXiv:2609.09226v1 Announce Type: new
Abstract: We introduce a probability-wave framework for modeling the collective behavior of interacting adaptive agents, deriving testable eigenmodes through a generalized behavioral intelligence (GBI) nonlocal probability-wave equation. This framework captures...
An Autonomous GeoAI Agent for Arctic Eco-Navigation
arXiv:2609.09374v1 Announce Type: new
Abstract: Arctic maritime navigation is becoming increasingly important as changing sea-ice conditions expand seasonal accessibility while simultaneously introducing substantial operational, environmental, and community risks. Arctic route planning is inherentl...
Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models
arXiv:2609.05437v1 Announce Type: new
Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `do not steal'). However, social intelligence depends not only on norm recognition, but also on anti...
CriticGen: Generation-Aware Evaluation as Actionable Feedback
arXiv:2609.05439v1 Announce Type: new
Abstract: Current evaluation methods for large language models are coarse-grained and decoupled from generation, producing generic explanations that fail to provide actionable feedback for model improvement. We propose CriticGen, a fine-grained, generation-awar...
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents
arXiv:2609.05441v1 Announce Type: new
Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dialogue history, not whether remembered facts change what a tool-using agent does. We present MERIT (M...
Damage-Aware Bandit Pruning for Vision and Language Transformers
arXiv:2609.05448v1 Announce Type: new
Abstract: Structured post-training pruning of transformers requires selecting complete functional units whose suppression causes limited degradation. We formulate structured-unit selection for language and vision transformers as a damage-aware multi-armed bandi...
Called to serve: Tech, research, and positive impact with Chris White
Lab Director Chris White has worked on research challenges with real-world implications—from new approaches to wartime data analysis to tools for combating human trafficking. He talks to program manager Weishung Liu about the influences that led to the work and more.
The post Called to serve: Tech, ...
Spectral-Target Physical Latent Structuring for JEPA-Style World Models
arXiv:2609.04264v1 Announce Type: new
Abstract: Latent world models have become increasingly popular as a method to predict and plan in latent space rather than pixel space. Recent architectures, such as LeWorldModel (LeWM), jointly train the encoder and predictor using regularization techniques li...
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
arXiv:2609.04265v1 Announce Type: new
Abstract: Existing post-hoc explainers for machine learning classifiers primarily focus on feature attribution, assigning importance scores to individual features. While valuable, this approach struggles to articulate the complex, combinatorial patterns that of...
A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations
arXiv:2609.04267v1 Announce Type: new
Abstract: Aerodynamic surrogate models trained on high-fidelity CFD data reproduce numerical predictions of both scalar outputs and entire fields accurately, yet their predictive fidelity is limited by systematic discrepancies between CFD and experimental obser...
Quantum-Assisted Memory-Efficient Training for Parameter-Intensive Wi-Fi-Based Human Activity Recognition
arXiv:2609.04271v1 Announce Type: new
Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of context-aware services. However, most existing Wi-Fi-based HAR systems rely on deep learning (DL) models ...
Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning
arXiv:2609.04272v1 Announce Type: new
Abstract: This study examines the ability of large language models (LLMs) to predict the risk of weather-related forced outages in the distribution grid in a zero-shot framework, without labeled training data. The problem is formulated as a binary severity clas...
arXiv:2609.04239v1 Announce Type: new
Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series (TS) foundation model (TSFM) tailored to financial forecasting. Recent TSFMs achieve strong zero-shot performance through large-scale pretraining. How...
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
arXiv:2609.04298v1 Announce Type: new
Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work mak...