AI Research Highlights

Sankalp Gilda, Shlok Gilda

Embeds Peircean reasoning as algebraic invariants in LLMs, enforcing logical structure—vital for builders of reliable reasoning agents where correctness, not just fluency, is non-negotiable.

Jeremy Qin, Maksym Andriushchenko

Introduces the first benchmark for evaluating LLMs on continuous numerical forecasting with prediction intervals, exposing critical gaps in real-world reasoning—essential for deploying LLMs in finance, healthcare, and policy decision systems.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

CALIBER introduces Bayesian low-rank adaptation for uncertainty-aware multimodal learning, enabling robust, efficient fine-tuning in low-resource settings—essential for builders deploying reliable multimodal systems under data scarcity.

Hyeongmeen Baik, Hamed Poursiami, Maryam Parsa et al.

First spiking neural network for sub-mW power converter health monitoring that decouples physics enforcement from temporal processing, enabling real-time edge inference without GPUs—critical for industrial IoT systems needing ultra-low-power reliability.

Yueyang Feng, Dipesh Kafle, Vladimir Gladshtein et al.

This work introduces a multi-modal verifier that dynamically adjusts LLM-generated specs to be both implementable and formally sound—enabling trustworthy, automated code generation for safety-critical systems.

Hyunseok Park, Jihyeon Kim, Jongeun Kim et al.

CHOP reduces RAG hallucinations by iteratively chunking and reassembling documents with LLMs—directly improving factual accuracy in production systems without requiring retraining or new embeddings.

Bhaskar Gurram

Reveals critical flaws in automated LLM agent evaluation and provides a human-validated benchmark with runtime mitigation, essential for building reliable tool-using agents in production systems.

Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian et al.

Reveals CoT prompting harms visual spatial reasoning in multimodal LLMs—forcing a rethink of reasoning paradigms in robotics, AR/VR, and vision-language systems where spatial accuracy is non-negotiable.

Xidong Wu, Yukuan Zhang, Yuqiong Ji et al.

Introduces privacy-preserving LLM routing using MPC, preventing data exposure during model selection—essential for enterprises deploying multi-provider LLM APIs under strict compliance regimes.

David Berghaus

EVIL replaces neural networks with evolved interpretable Python code for zero-shot time series inference, enabling deployable, transparent models without retraining—critical for real-time systems needing explainability and low resource use.

Xiao Wang, Zezhong Zhang, Isaac Lyngaas et al.

A linear-complexity global attention mechanism enables exascale generative data assimilation, dramatically improving uncertainty quantification in weather/climate models—critical for real-time extreme event prediction systems.

Hikaru Shindo, Hanzhao Lin, Lukas Helff et al.

SocialGrid provides the first benchmark for social reasoning in embodied multi-agent systems, exposing critical gaps in LLM agents' planning and deception detection—essential for building trustworthy autonomous agents.

Geunyoung Jung, Soohong Kim, Inseok Kong et al.

APC introduces a lightweight, transferable counterattack module that boosts 3D point cloud robustness without sacrificing accuracy—critical for real-time systems facing adversarial inputs in robotics or autonomous driving.

Eren Unlu

Proposes SSTA-32, a diagnostic framework to evaluate if agents can diagnose task blockers before acting—critical for building trustworthy autonomous systems that avoid costly errors in open-ended environments.

Yao Chen, Jiawei Sheng, Wenyuan Zhang et al.

Proposes stepwise attention distillation to transfer dynamic reasoning focus from large to small models, significantly improving small-model reasoning without requiring larger architectures—key for efficient deployment in resource-constrained systems.