- Constant-Time Motion Planning with Manipulation Behaviors
Nayesha Gandotra, Itamar Mishani, Maxim Likhachev · Nov 30, 2025 · Citations: 0
One of the key barriers is the lack of motion planning algorithms that can provide verifiable guarantees for safety, efficiency and reliability.
- OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models
Michael Siebenmann, Javier Argota Sánchez-Vaquerizo, Stefan Arisona, Krystian Samp, Luis Gisler · Nov 30, 2025 · Citations: 0
The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs.
- Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval
Hao Wu, Prateek Saxena · Nov 30, 2025 · Citations: 0
- OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion
Sai Koneru, Matthias Huck, Jan Niehues · Nov 28, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Writing in Symbiosis: Mapping Human Creative Agency in the AI Era
Vivan Doshi, Mengyuan Li · Nov 28, 2025 · Citations: 0
The proliferation of Large Language Models (LLMs) raises a critical question about what it means to be human when we share an increasingly symbiotic relationship with persuasive and creative machines.
- AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
Yibin Wen, Qingmei Li, Zi Ye, Jiarui Zhang, Zurong Mai · Nov 28, 2025 · Citations: 0
However, while several Visual Question Answering (VQA) datasets and benchmarks have been developed to assess VLM performance, they often fail to effectively evaluate the critical reasoning and problem-solving skills needed in complex…
- Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM
Mengjie Liu, Jiahui Peng, Wenchang Ning, Pei Chu, Jiantao Qiu · Nov 28, 2025 · Citations: 0
- ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking
Davide Donno, Donatello Elia, Gabriele Accarino, Marco De Carlo, Enrico Scoccimarro · Nov 28, 2025 · Citations: 0
Long Horizon
ByteStorm is benchmarked with state-of-the-art deterministic trackers on the main global TC formation basins.
- STELLAR: Structure-guided LLM Assertion Retrieval and Generation for Formal Verification
Saeid Rajabi, Chengmo Yang, Satwik Patnaik · Nov 28, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
Alberto Compagnoni, Marco Morini, Sara Sarto, Federico Cocchi, Davide Caffagni · Nov 27, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel
Jinjun Yi, Zhixin Zhao, Yitao Hu, Ke Yan, Weiwei Sun · Nov 27, 2025 · Citations: 0
- Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
Inha Kang, Eunki Kim, Wonjeong Ryu, Jaeyo Shin, Seungjun Yu · Nov 27, 2025 · Citations: 0
Long Horizon
To address this gap, we construct and release the real-world observations and high-resolution CMAQ-OBS dataset for East Asia, reducing regional error by 59.5% and enabling real-time 48-120 hour forecasts critical for public health alerts.
- Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of Agents
Yue Zhong, Yongju Tong, Jiawen Kang, Minghui Dai, Hong-Ning Dai · Nov 27, 2025 · Citations: 0
- MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis
Chunzheng Zhu, Yangfang Lin, Shen Chen, Yijun Wang, Jianxin Lin · Nov 27, 2025 · Citations: 0
- When Models Fabricate Credentials: Measuring How Professional Identity Suppresses Honest Self-Representation
Alex Diep · Nov 26, 2025 · Citations: 0
- E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lv, Hao Liu · Nov 26, 2025 · Citations: 0
- A Systematic Study of In-the-Wild Model Merging for Large Language Models
Oğuz Kağan Hitit, Leander Girrbach, Zeynep Akata · Nov 26, 2025 · Citations: 0
To evaluate this setting, we present a large-scale, systematic evaluation of "in-the-wild" model merging of heterogeneous experts, that may have been trained on overlapping or conflicting objectives.
- Steering Awareness: Detecting Activation Steering from Within
Joshua Fonseca Rivera, David Demitri Africa · Nov 26, 2025 · Citations: 0
Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention.
- PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
Robert Belanec, Branislav Pecher, Ivan Srba, Maria Bielikova · Nov 26, 2025 · Citations: 0
Despite the advances in PEFT methods, current evaluations remain limited (in terms of evaluated models and datasets) and difficult to reproduce.
- RosettaSpeech: Zero-Shot Speech-to-Speech Translation without Parallel Speech
Zhisheng Zheng, Xiaohang Sun, Tuan Dinh, Abhishek Yanamandra, Abhinav Jain · Nov 26, 2025 · Citations: 0
Empirical evaluations on the CVSS-C benchmark demonstrate that RosettaSpeech achieves state-of-the-art zero-shot performance, surpassing leading baselines by significant margins - achieving ASR-BLEU scores of 25.17 for German-to-English…
- Structured Prompts Improve Evaluation of Language Models
Asad Aali, Muhammad Ahmed Mohsin, Vasiliki Bikia, Arnav Singhvi, Richard Gaus · Nov 25, 2025 · Citations: 0
We present a reproducible DSPy+HELM framework for studying how prompt choice impacts reported benchmark outcomes.
- RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerlines
Roman Naeem, David Hagerman, Jennifer Alvén, Fredrik Kahl · Nov 25, 2025 · Citations: 0
Long Horizon
We further introduce an efficient non-maximum suppression algorithm for spatial tree graphs to merge duplicate branches and extend evaluation metrics to be radius-aware for robust comparison.
- SPHINX: A Synthetic Environment for Visual Perception and Reasoning
Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae, Nidhi Rastogi · Nov 25, 2025 · Citations: 0
- CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents
Haebin Seong, Sungmin Kim, Yongjun Cho, Myunchul Joe, Geunwoo Kim · Nov 25, 2025 · Citations: 0
- Human-computer interactions predict mental health
Veith Weilnhammer, Jefferson Ortega, David Whitney · Nov 25, 2025 · Citations: 0
Here, we show that everyday human-computer interactions encode mental health with biomarker accuracy.
- Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection
Daniel Harari, Michael Sidorov, Chen Shterental, Liel David, Abrham Kahsay Gebreselasie · Nov 25, 2025 · Citations: 0
250 AMTurk human annotators labeled core interaction events, particularly when and where objects and agents become attached (`contact') or detached (`release').
- The Metaphysics We Train: A Heideggerian Reading of Machine Learning
Heman Shakeri · Nov 25, 2025 · Citations: 0
Third, AI's lack of existential structure, specifically the absence of Care (Sorge), is genuinely explanatory: it illuminates why AI systems have no internal resources for questioning their own optimization imperatives, and why they…
- Foundry: Distilling 3D Foundation Models for the Edge
Guillaume Letellier, Siddharth Srivastava, Frédéric Jurie, Gaurav Sharma · Nov 25, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Pedestrian Crossing Intention Prediction Using Multimodal Fusion Network
Yuanzhe Li, Steffen Müller · Nov 25, 2025 · Citations: 0
- A Machine Learning Approach for Detection of Mental Health Conditions and Cyberbullying from Social Media
Edward Ajayi, Martha Kachweka, Mawuli Deku, Emily Aiken · Nov 25, 2025 · Citations: 0
We conducted a comprehensive evaluation comparing traditional lexical models, hybrid approaches, and several end-to-end fine-tuned transformers.
- Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
Chenliang Li, Adel Elmahdy, Alex Boyd, Zhongruo Wang, Siliang Zeng · Nov 25, 2025 · Citations: 0
Long Horizon
To address these challenges, we propose SORL, Stabilizing Off-Policy Reinforcement Learning for Long-Horizon Agent Training.
- Gender Bias in Emotion Recognition by Large Language Models
Maureen Herbert, Katie Sun, Angelica Lim, Yasaman Etesam · Nov 24, 2025 · Citations: 0
- Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
James R. M. Black, Moritz S. Hanke, Aaron Maiwald, Tina Hernandez-Boussard, Oliver M. Crook · Nov 24, 2025 · Citations: 0
These models, referred to as genomic language models (gLMs), have demonstrated impressive predictive and generative capabilities, raising concerns that such models may also enable misuse, for instance via the generation of genomes for…
- CDLM: Consistency Diffusion Language Models For Faster Sampling
Minseo Kim, Chenfeng Xu, Coleman Hooper, Harman Singh, Ben Athiwaratkun · Nov 24, 2025 · Citations: 0
The full training and evaluation code is available at https://github.com/SqueezeAILab/CDLM.
- Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning
Jian Lu · Nov 24, 2025 · Citations: 0
- Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
Yuqiu Jiang, Xiaozhen Qiao, Yifan Chen, Ye Zheng, Zhe Sun · Nov 24, 2025 · Citations: 0
- NI-Tex: Non-isometric Image-based Garment Texture Generation
Hui Shan, Ming Li, Haitao Yang, Kai Zheng, Sizhe Zheng · Nov 24, 2025 · Citations: 0
- Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models
Wangjiaxuan Xin · Nov 24, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SO-Bench: A Structural Output Evaluation of Multimodal LLMs
Di Feng, Kaixin Ma, Feng Nan, Haofeng Chen, Bohan Zhai · Nov 23, 2025 · Citations: 0
Multimodal large language models (MLLMs) are increasingly deployed in real-world, agentic settings where outputs must not only be correct, but also conform to predefined data schemas.
- Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives
Kai Jiang, Siqi Huang, Xiangyu Chen, Jiawei Shao, Hongyuan Zhang · Nov 23, 2025 · Citations: 0
- Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
Yi Zhang, Chao Zhang, Zijian Li, Tianxiang Xu, Kunyu Zhang · Nov 23, 2025 · Citations: 0
- SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Tram Dinh · Nov 23, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Scaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations
Plein Versace · Nov 23, 2025 · Citations: 0
- NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields
Plein Versace · Nov 23, 2025 · Citations: 0
- Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri, Eric Granger · Nov 23, 2025 · Citations: 0
- Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
Dachuan Zhao, Weiyue Li, Zhenda Shen, Yushu Qiu, Bowen Xu · Nov 22, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization
Jianghao Wu, Yasmeen George, Jin Ye, Yicheng Wu, Daniel F. Schmidt · Nov 22, 2025 · Citations: 0
Across eight benchmarks spanning multimodal VQA, text-only reasoning, \method consistently improves Pass@1 over TTRL while avoiding response-length collapse and yielding more stable training dynamics on both LLM and MLLM backbones.
- Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation
Scott Merrill, Shashank Srivastava · Nov 21, 2025 · Citations: 0
Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior.
- A cross-species neural foundation model for end-to-end speech decoding
Yizi Zhang, Linyang He, Chaofei Fan, Tingkai Liu, Han Yu · Nov 21, 2025 · Citations: 0
In a cascaded setting with an n-gram LM, the pretrained encoder establishes a new state-of-the-art (SOTA) on the Brain-to-Text '24 and '25 benchmarks.
- REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
Binger Chen, Tacettin Emre Bök, Behnood Rasti, Volker Markl, Begüm Demir · Nov 21, 2025 · Citations: 0
- A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
Wei-Kai Chang, Rajiv Khanna · Nov 21, 2025 · Citations: 0
- DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams
Ginés Carreto Picón, Peng Yuan Zhou, Qi Zhang, Alexandros Iosifidis · Nov 21, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Estonian WinoGrande Dataset: Comparative Analysis of LLM Performance on Human and Machine Translation
Marii Ojastu, Hele-Andra Kuulmets, Aleksei Dorkin, Marika Borovikova, Dage Särg · Nov 21, 2025 · Citations: 0
In this paper, we present a localized and culturally adapted Estonian translation of the test set from the widely used commonsense reasoning benchmark, WinoGrande.
- HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation
Jiajun Zhang, Shijia Luo, Ruikang Zhang, Qi Su · Nov 21, 2025 · Citations: 0
Pairwise Preference Long Horizon
Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation.
- MUCH: A Multilingual Claim Hallucination Benchmark
Jérémie Dentan, Alexi Canesse, Davide Buscaldi, Aymen Shabou, Sonia Vanier · Nov 21, 2025 · Citations: 0
We introduce MUCH, the first claim-level UQ benchmark designed for fair and reproducible evaluation of future methods under realistic conditions.
- Bridging Symbolic Control and Neural Reasoning in LLM Agents: Structured Cognitive Loop with a Governance Layer
Myung Ho Kim · Nov 21, 2025 · Citations: 0
Long Horizon
Large language model agents suffer from fundamental architectural problems: entangled reasoning and execution, memory volatility, and uncontrolled action sequences.
- ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers
Seyed Mohssen Ghafari, Ronny Kol, Juan C. Quiroz, Nella Luan, Monika Patial · Nov 20, 2025 · Citations: 0
Experimental results demonstrate that our proposed metric identifies redundancy in LLM outputs, offering a practical tool for automated evaluation of response brevity in conversational AI systems without the need for ground truth human…
- PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin · Nov 20, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report
Yan Chen, Yu Zou, Jialei Zeng, Haoran You, Xiaorui Zhou · Nov 20, 2025 · Citations: 0
- German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
Jens Rupprecht, Leon Fröhling, Claudia Wagner, Markus Strohmaier · Nov 19, 2025 · Citations: 0
The use of Large Language Models (LLMs) for simulating human perspectives via persona prompting is gaining traction in computational social science.