Papers
Research papers from arXiv and related sources
CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performance. However, Hidd...
Alexandre Le Mercier, Thomas Demeester, Chris Develder
Long-Context Encoder Models for Polish Language Understanding
While decoder-only Large Language Models (LLMs) have recently dominated the NLP landscape, encoder-only architectures remain a cost-effective and parameter-efficient standard for discriminative tas...
Sławomir Dadas, Rafał Poświata, Marek Kozłowski, Małgorzata Grębowiec, Michał Perełkiewicz, Paweł...
Shifted-geodesic approximation for spinning-body gravitational wave fluxes
We present a shifted-geodesic framework for computing gravitational-wave fluxes from spinning test bodies moving on bound orbits of Kerr black holes. The method provides a simple and efficient mean...
Lisa V. Drummond, Scott A. Hughes, Viktor Skoupý, Philip Lynch, Gabriel Andres Piovano
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely sto...
Łukasz Borchmann, Jordy Van Landeghem, Michał Turski, Shreyansh Padarha, Ryan Othniel Kearns, Ada...
BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning
Understanding freely moving animal behavior is central to neuroscience, where pose estimation and behavioral understanding form the foundation for linking neural activity to natural actions. Yet bo...
Jingyang Ke, Weihan Li, Amartya Pradhan, Jeffrey Markowitz, Anqi Wu
QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions
Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult to detect with current metrics. Existing data sele...
Jiayin Lei, Ming Ma, Yunxi Duan, Chenxi Li, Tianming Yang
Investigating student perceptions of creativity and generative ai in computational physics
Generative Artificial Intelligence (gen-AI) is rapidly becoming more integrated into today's classrooms in all ranges of education. In higher education, Gen-AI is often seen as a resource for stude...
Pachi Her, Patti Hamerski
LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation
The rapid advancement of large language models (LLMs) has accelerated progress toward universal AI assistants. However, existing benchmarks for personalized assistants remain misaligned with real-w...
Feiyu Duan, Xuanjing Huang, Zhongyu Wei
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
While scaling laws guide compute allocation for LLM pre-training, analogous prescriptions for reinforcement learning (RL) post-training of large language models (LLMs) remain poorly understood. We ...
Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang,...
Linking Perception, Confidence and Accuracy in MLLMs
Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do model...
Yuetian Du, Yucheng Wang, Rongyu Zhang, Zhijie Xu, Boyu Yang, Ming Kong, Jie Liu, Qiang Zhu
Automatic Generation of High-Performance RL Environments
Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specialized engineering. We present a reusable recipe - a gen...
Seth Karten, Rahul Dev Appapogu, Chi Jin
TopoBench: Benchmarking LLMs on Hard Topological Reasoning
Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large l...
Mayug Maniparambil, Nils Hoehing, Janak Kapuriya, Arjun Karuvally, Ellen Rushe, Anthony Ventresqu...
Increasing intelligence in AI agents can worsen collective outcomes
When resources are scarce, will a population of AI agents coordinate in harmony, or descend into tribal chaos? Diverse decision-making AI from different developers is entering everyday devices -- f...
Neil F. Johnson
Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions
Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforwa...
Tae-Eun Song
CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance
We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not uniform across the...
Leo Lin, Shivansh Patel, Jay Moon, Svetlana Lazebnik, Unnat Jain
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Serving these models...
Jae-Won Chung, Jeff J. Ma, Jisang Ahn, Yizhuo Liang, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury
SommBench: Assessing Sommelier Expertise of Language Models
With the rapid advances of large language models, it becomes increasingly important to systematically evaluate their multilingual and multicultural capabilities. Previous cultural evaluation benchm...
William Brach, Tomas Bedej, Jacob Nielsen, Jacob Pichna, Juraj Bedej, Eemeli Saarensilta, Julie D...
On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
Reinforcement learning (RL) with outcome-based rewards has achieved significant success in training large language model (LLM) agents for complex reasoning tasks. However, in active reasoning where...
Deyu Zou, Yongqiang Chen, Fan Feng, Mufei Li, Pan Li, Yu Gong, James Cheng
To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times
Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate ...
Thomas Hikaru Clark, Carlos Arriaga, Javier Conde, Gonzalo Martínez, Pedro Reviriego
Human-Centred LLM Privacy Audits: Findings and Frictions
Large language models (LLMs) learn statistical associations from massive training corpora and user interactions, and deployed systems can surface or infer information about individuals. Yet people ...
Dimitri Staufer, Kirsten Morehouse, David Hartmann, Bettina Berendt