Ward: Newsss

330

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection

arXiv:2504.11900v3 Announce Type: replace
Abstract: Stories are a fundamental aspect of human experience. Engaging deeply with stories and spotting plot holes -- inconsistencies in a storyline that break the internal logic or rules of a story's world -- requires nuanced reasoning skills, including …

321

CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?

arXiv:2512.16755v1 Announce Type: new
Abstract: Vision-Language Models (VLMs) have made significant progress in explicit instruction-based navigation; however, their ability to interpret implicit human needs (e.g., "I am thirsty") in dynamic urban environments remains underexplored. This paper intr…

322

OpenAI adds new teen safety rules to ChatGPT as lawmakers weigh AI standards for minors

OpenAI updated its guidelines for how its AI models should behave with users under 18, and published new AI literacy resources for teens and parents. Still, questions remain about how well policies translate into practice.

321

Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation

arXiv:2512.16913v1 Announce Type: new
Abstract: In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset b…

330

Social Story Frames: Contextual Reasoning about Narrative Intent and Reception

arXiv:2512.15925v1 Announce Type: new
Abstract: Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences about narrative intent or judgments about characters. Yet, computational models of reader response are limited, preventing nuanced analyses. To address t…

329

D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos

arXiv:2507.05859v3 Announce Type: replace
Abstract: Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splatting methods couple reconstruction with optimization-dependent compres…

310

Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models

arXiv:2511.07503v3 Announce Type: replace
Abstract: The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explores the use of language models (LMs) for the generation of synthetic …

301

Meta is developing a new image and video model for a 2026 release, report says

The company is working on an image and video model and new text-based model, which aids with coding.

243

DAG Learning from Zero-Inflated Count Data Using Continuous Optimization

arXiv:2512.16233v1 Announce Type: cross
Abstract: We address network structure learning from zero-inflated count data by casting each node as a zero-inflated generalized linear model and optimizing a smooth, score-based objective under a directed acyclic graph constraint. Our Zero-Inflated Continuo…

233

Learning to Wait: Synchronizing Agents with the Physical World

arXiv:2512.16262v1 Announce Type: new
Abstract: Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing environment-side…

222

Hybrid Quantum-Classical Ensemble Learning for S\&P 500 Directional Prediction

arXiv:2512.15738v1 Announce Type: new
Abstract: Financial market prediction is a challenging application of machine learning, where even small improvements in directional accuracy can yield substantial value. Most models struggle to exceed 55--57\% accuracy due to high noise, non-stationarity, and …

221

Kodiak AI looks to transform trucking with autonomous tech, IoT connectivity

5G telematics and ThingSpace IoT management services enable autonomous vehicle technology operating model and manage massive amounts of data generated from its driverless trucks

227

Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization

arXiv:2505.21423v2 Announce Type: replace
Abstract: A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this theoretically, re…

210

Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model

arXiv:2512.16251v1 Announce Type: cross
Abstract: We introduce the \textit{Consensus-Bottleneck Asset Pricing Model} (CB-APM), a partially interpretable neural network that replicates the reasoning processes of sell-side analysts by capturing how dispersed investor beliefs are compressed into asset…

210

Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game

arXiv:2512.16626v1 Announce Type: new
Abstract: We introduce Stackelberg Learning from Human Feedback (SLHF), a new framework for preference optimization. SLHF frames the alignment problem as a sequential-move game between two policies: a Leader, which commits to an action, and a Follower, which re…

120

On alternating-conjugate splitting methods

arXiv:2503.08453v2 Announce Type: replace
Abstract: The new class of alternating-conjugate splitting methods is presented and analyzed. They are obtained by concatenating a given composition involving complex coefficients with the same composition but with the complex conjugate coefficients. We sho…

122

Sharpness-aware Federated Graph Learning

arXiv:2512.16247v1 Announce Type: new
Abstract: One of many impediments to applying graph neural networks (GNNs) to large-scale real-world graph data is the challenge of centralized training, which requires aggregating data from different organizations, raising privacy concerns. Federated graph lea…

128

Towards AI-Supported Research: a Vision of the TIB AIssistant

arXiv:2512.16447v1 Announce Type: new
Abstract: The rapid advancements in Generative AI and Large Language Models promise to transform the way research is conducted, potentially offering unprecedented opportunities to augment scholarly workflows. However, effectively integrating AI into research re…

111

SceneDiff: A Benchmark and Method for Multiview Object Change Detection

arXiv:2512.16908v1 Announce Type: new
Abstract: We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Detecting such changes is important for many applications, such as robotic ti…

109

Input Reduction Enhanced LLM-based Program Repair

arXiv:2507.15251v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have shown great potential in Automated Program Repair (APR). Test inputs, being crucial for reasoning the root cause of failures, are always included in the prompt for LLM-based APR. Unfortunately, LLMs struggle to re…