Ward: Newsss

222

Confidence Calibration in Vision-Language-Action Models

arXiv:2507.17383v2 Announce Type: replace
Abstract: Trustworthy robot behavior requires not only high levels of task success but also that the robot can reliably quantify how likely it is to succeed. To this end, we present a first-of-its-kind study of confidence calibration in vision-language-acti…

227

Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering

arXiv:2512.18551v1 Announce Type: new
Abstract: In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give me a neolog…

329

DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis

arXiv:2512.19331v1 Announce Type: new
Abstract: Whole Slide Images (WSIs) are typically analyzed using multiple instance learning (MIL) methods. However, the scale and heterogeneity of WSIs generate highly redundant and dispersed information, making it difficult to identify and integrate discrimina…

221

LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation

arXiv:2512.18329v1 Announce Type: new
Abstract: Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating…

111

SoK: Are Watermarks in LLMs Ready for Deployment?

arXiv:2506.05594v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual property violations and potent…

120

Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models

arXiv:2512.18910v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) combine visual and textual representations to enable rich reasoning capabilities. However, the high computational cost of processing dense visual tokens remains a major bottleneck. A critical component in this …

110

Modular Automatic Complexity Analysis of Recursive Integer Programs

arXiv:2512.18851v1 Announce Type: new
Abstract: In earlier work, we developed a modular approach for automatic complexity analysis of integer programs. However, these integer programs do not allow non-tail recursive calls or subprocedures. In this paper, we consider integer programs with function c…

319

Explainable Graph Spectral Clustering For GloVe-like Text Embeddings

arXiv:2508.14075v2 Announce Type: replace
Abstract: In a previous paper, we proposed an introduction to the explainability of Graph Spectral Clustering results for textual documents, given that document similarity is computed as cosine similarity in term vector space.
In this paper, we generalize…

322

Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning

arXiv:2512.18604v1 Announce Type: new
Abstract: Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-bas…

222

Sharpness-Controlled Group Relative Policy Optimization with Token-Level Probability Shaping

arXiv:2511.00066v2 Announce Type: replace
Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. This paper revisits GRPO from a…

342

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector

arXiv:2503.07982v3 Announce Type: replace
Abstract: High-quality instance and panoptic segmentation has traditionally relied on dense instance-level annotations such as masks, boxes, or points, which are costly, inconsistent, and difficult to scale. Unsupervised and weakly-supervised approaches red…

420

Socratic Students: Teaching Language Models to Learn by Asking Questions

arXiv:2512.13102v2 Announce Type: replace
Abstract: Large Language Models (LLMs) excel at static interactions, where they answer user queries by retrieving knowledge encoded in their parameters. However, in many real-world settings, such as educational tutoring or medical assistance, relevant infor…

219

VERDI: VLM-Embedded Reasoning for Autonomous Driving

arXiv:2505.15925v3 Announce Type: replace
Abstract: While autonomous driving (AD) stacks struggle with decision making under partial observability and real-world complexity, human drivers are capable of commonsense reasoning to make near-optimal decisions with limited information. Recent work has a…

320

FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis

arXiv:2512.18073v1 Announce Type: new
Abstract: Multimodal LLMs (MLLMs) have gained significant traction in complex data analysis, visual question answering, generation, and reasoning. Recently, they have been used for analyzing the biometric utility of iris and face images. However, their capabili…

218

Executorch: On-device AI across mobile, embedded and edge for PyTorch

Comments

332

Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification

arXiv:2508.06831v2 Announce Type: replace
Abstract: Adapting person re-identification (reID) models to new target environments remains a challenging problem that is typically addressed using unsupervised domain adaptation (UDA) methods. Recent works show that when labeled data originates from sever…

321

No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

arXiv:2508.01171v2 Announce Type: replace
Abstract: We introduce SPFSplat, an efficient framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training or inference. It employs a shared feature extraction backbone, enabling simultaneous prediction …

222

Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting

arXiv:2512.19651v1 Announce Type: new
Abstract: Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment. While supervised learning approaches dominate this field, the scarcity and high cost of annotated data f…

220

A Comprehensive Survey on Generative AI for Video-to-Music Generation

arXiv:2502.12489v2 Announce Type: replace-cross
Abstract: The burgeoning growth of video-to-music generation can be attributed to the ascendancy of multimodal generative models. However, there is a lack of literature that comprehensively combs through the work in this field. To fill this gap, this …

118

Toward Human-Centered AI-Assisted Terminology Work

arXiv:2512.18859v1 Announce Type: new
Abstract: The rapid diffusion of generative artificial intelligence is transforming terminology work. While this technology promises gains in efficiency, its unstructured adoption risks weakening professional autonomy, amplifying bias, and eroding linguistic an…