Papers
Research papers from arXiv and related sources
ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existi...
Weixiang Zhao, Haozhen Li, Yanyan Zhao, xuda zhi, Yongbo Huang, Hao He, Bing Qin, Ting Liu
CMMR-VLN: Vision-and-Language Navigation via Continual Multimodal Memory Retrieval
Although large language models (LLMs) are introduced into vision-and-language navigation (VLN) to improve instruction comprehension and generalization, existing LLM- based VLN lacks the ability to ...
Haozhou Li, Xiangyu Dong, Huiyan Jiang, Yaoming Zhou, Xiaoguang Ma
MJ1: Multimodal Judgment via Grounded Verification
Multimodal judges struggle to ground decisions in visual evidence. We present MJ1, a multimodal judge trained with reinforcement learning that enforces visual grounding through a structured grounde...
Bhavesh Kumar, Dylan Feng, Leonard Tang
On the Feasibility and Opportunity of Autoregressive 3D Object Detection
LiDAR-based 3D object detectors typically rely on proposal heads with hand-crafted components like anchor assignment and non-maximum suppression (NMS), complicating training and limiting extensibil...
Zanming Huang, Jinsu Yoo, Sooyoung Jeon, Zhenzhen Liu, Mark Campbell, Kilian Q Weinberger, Bharat...
ZK-ACE: Identity-Centric Zero-Knowledge Authorization for Post-Quantum Blockchain Systems
Post-quantum signature schemes introduce kilobyte-scale authorization artifacts when applied directly to blockchain transaction validation. A widely considered mitigation is to verify post-quantum ...
Jian Sheng Wang
Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs
With the rapid advancement of human science and technology, problems in industrial scenarios are becoming increasingly challenging, bringing significant challenges to traditional algorithm design. ...
Chen Lu, Ke Xue, Chengrui Gao, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, Chao Qian, Zhi-Hua Zhou
WeldAR: Augmenting Live Hands-On Training with In-Situ Guidance for Novice Learners
Extended Reality (XR) systems for physical skill training have largely emphasized simulation rather than real-time in-situ instruction. We present WeldAR, an Augmented Reality (AR) system with five...
Chuhan, Xu, Lia Sparingga Purnamasari, Zhenfang Chen, Daragh Byrne, Dina El-Zanfaly
RL unknotter, hard unknots and unknotting number
We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for navigating Reidemeister moves. The pipeline applies to ar...
Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer
ConnChecker: Automated Root-Cause Analysis for Formal Connectivity Check via Graph
Formal connectivity checking offers scalable verification of signal paths in complex SoC designs, but debugging counterexamples remains a manual and time-consuming process. ConnChecker introduces a...
Do Ngoc Tiep, Nguyen Linh Anh, Luu Danh Minh
Condition-Triggered Cryptographic Asset Control via Dormant Authorization Paths
Control of encrypted digital assets is traditionally equated with permanent possession of private keys, a model that precludes regulatory supervision, conditional delegation, and legally compliant ...
Jian Sheng Wang
Hard/Soft NLoS Detection via Combinatorial Data Augmentation for 6G Positioning
A key enabler for meeting the stringent requirements of 6G positioning is the ability to exploit site-dependent information governing line-of-sight (LoS) and non-line-of-sight (NLoS) propagation. H...
Sang-Hyeok Kim, Seung Min Yu, Jihong Park, Seung-Woo Ko
Omnidirectional Humanoid Locomotion on Stairs via Unsafe Stepping Penalty and Sparse LiDAR Elevation Mapping
Humanoid robots, characterized by numerous degrees of freedom and a high center of gravity, are inherently unstable. Safe omnidirectional locomotion on stairs requires both omnidirectional terrain ...
Yuzhi Jiang, Yujun Liang, Junhao Li, Han Ding, Lijun Zhu
SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training
Large language models (LLMs) have transformed the software engineering landscape. Recently, numerous LLM-based agents have been developed to address real-world software issue fixing tasks. Despite ...
Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, Cuiyun Gao
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich representations of la...
Sunghyun Baek, Jaemyung Yu, Seunghee Koh, Minsu Kim, Hyeonseong Jeon, Junmo Kim
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptabili...
Hui Liu, Kecheng Chen, Jialiang Wang, Xianming Liu, Wenya Wang, Haoliang Li
Effective and flexible depth-based inference for functional parameters
For hypothesis testing of functional parameters, given a functional statistic $T_n$ and a functional depth $D$ with respect to the distribution $P_n$ of $T_n$, we propose the depth value $DT_n \equ...
Hyemin Yeon
Structural aging of a cohesive and amorphous granular solid under cyclic loading
We investigate how cyclic loading evolves the structure and deformation behaviors of a granular raft composed of particles floating at an air-oil interface. The raft has a disordered particle packi...
William Hobson-Rhoades, Douglas J Durian, Yue Fan, Hongyi Xiao
A Lock-Free, Fully GPU-Resident Architecture for the Verification of Goldbach's Conjecture
We present a fully device-resident, multi-GPU architecture for the large-scale computational verification of Goldbach's conjecture. In prior work, a segmented double-sieve eliminated monolithic VRA...
Isaac Llorente-Saguer
Intentional Deception as Controllable Capability in LLM Agents
As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception...
Jason Starace, Terence Soule
New results and tests for stochastic dominance between linear combinations
Convex combinations of i.i.d. random variables without a finite mean can behave in a strikingly different way from the finite-mean case: as the weight vector becomes more balanced, the resulting co...
Tommaso Lando, Paulo Eduardo Oliveira