AI alignment, RLHF, harmlessness, robustness, and LLM jailbreak research.
Ivan Lerner, Jean Feydy, Alexandre Kalimouttou et al.
Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpret…
Haidong Zhao, Nikolaos Georgantas
Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization an…
Bowen Sun, Chaozhuo Li, Yaodong Yang et al.
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collecti…
Anietta Weckauff, Yuchen Zhang, Maksym Andriushchenko
Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignment (EM). While prior work has found a correlatio…
Matti Berthold, Lydia Blümel, Giovanni Buraglio et al.
This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on bipolar set-based argumentation frameworks (BSA…
Nina Seron-Abouelfadil, Poppy Fynes
Sign languages, of any geographical or accentual variation, understandably face continuous scrutiny under the ever present popularity of verbal dictation and audism. Through this, many potential probl…
Prashant Kulkarni
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack pa…
Shreya Chappidi, Jatinder Singh
Responsible AI research typically focuses on examining the use and impacts of deployed AI systems. Yet, there is currently limited visibility into the pre-deployment decisions to pursue building such …
Jialu Shen, Han Lyu, Suyang Zhong et al.
Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (MLLMs) due to their unstructured and domain-spec…
Ivan Bercovich
Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so doe…
Yujun Wu, Dongxu Zhang, Xinchen Li et al.
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not…
Feiyu Wu, Xu Zheng, Zhuocheng Wang et al.
Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically reliable training objectives. Existing work has focus…
Zainab Rehan, Christian Medeiros Adriano, Sona Ghahremani et al.
Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in f…
Lincan Li, Zheng Chen, Yushun Dong
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether co…
Sudong Wang, Weiquan Huang, Xiaomin Yu et al.
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). H…
Jeanne Monnier, Thomas George, Frédéric Guyard et al.
Fairness in machine learning remains challenging due to its ethical complexity, the absence of a universal definition, and the need for context-specific bias metrics. Existing methods still struggle w…
Taslim Jamal Arif, Kuldeep Singh
Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based SQL matching or sche…
Ce Chen, Yi Ren, Yuanming Li et al.
Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this f…
Johannes Pfau, Panagiotis Vrettis
Since the dawn of Trading Card Games, the genre has grown into a multi-billion-dollar industry engaging millions of analog and digital players worldwide. Popular TCGs rely on regular updates, balance …
Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll
Integrating multimodal foundation models into enterprise ecosystems presents a fundamental software architecture challenge. Architects must balance competing quality attributes: the high latency and n…
Rogério Almeida Gouvêa, Gian-Marco Rignanese
While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computationally predicted materials is insufficient; autom…
Shuo Jiang, Jianxi Luo
Design Structure Matrix (DSM) modularization, the task of partitioning system elements into cohesive modules, is a fundamental combinatorial challenge in engineering design. Traditional methods treat …
Zihao Li, Jiaru Zou, Feihao Fang et al.
Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world p…
Tianyuan Wu, Chaokun Chang, Lunxi Cao et al.
Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault toleranc…
Xubin Luo, Yang Cheng
AI inference is becoming a persistent and geographically distributed source of electricity demand. Unlike many traditional electrical loads, inference workloads can sometimes be executed away from the…
Jackson Vonderhorst, Kuangshi Ai, Haichao Miao et al.
This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language inst…
Chenxin Li, Zhengyang Tang, Huangxin Lin et al.
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and gra…
Fangming Cui, Ruixiao Zhu, Cheng Fang et al.
Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large…
Giuseppe Arbore, Andrea Sillano, Luigi De Russis
Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's ag…
Rahul Ramachandran, Nidhi Jha, Muthukumaran Ramasubramanian
We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial-and-error approaches…
Sign up free and get daily digests tailored to your research interests.
Sign up free