Research
Research
Research
Research
91,526+ open-access research outputs.
Large language models (LLMs) have shown strong performance on legal benchmarks, including multiple-choice components of bar exams. However, their capacity for generating open-ended legal reasoning in …
Mechanistic interpretability research on emotion in large language models -- linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steering vector extraction…
Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are correct, the reasoning b…
We investigate narrative agency in human-LLM creative co-writing, asking who drives story development in turn-based collaboration. Using a new corpus of 87 human-LLM co-written stories, we apply senti…
Spectral problems governed by differential operators underpin a wide range of physical systems, yet remain computationally challenging because their spectra depend sensitively on continuous parameters…
Early, tool-free prediction of post-synthesis timing remains a key obstacle to rapid RTL iteration. We introduce TimingLLM, a two-stage retrieval-augmented LLM pipeline that estimates worst negative s…
Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising v…
In the digital era, personal data, particularly sensitive identifiers such as the Social Security Number and National Identification Number, have become a highly valuable asset, raising significant co…
Safety specifications in cyber-physical systems (CPS) capture the operational conditions the system must satisfy to operate safely within its intended environment. As operating environments evolve, op…
A search is presented for massive narrow-width resonances in the mass range of $1\text{-}4.5\,\text{TeV}$ decaying into pairs of Higgs bosons (HH), using proton-proton collision data at a center-of-ma…
Reward hacking in code generation, where models exploit evaluation loopholes to obtain full reward without correctly solving the tasks, poses a critical challenge for Reinforcement Learning (RL) and t…
We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activation-gradient second moments, we show that loss s…
The invariant mass spectrum of $e^+e^-$ pairs produced in high-energy Pb-emulsion collisions at 160 A GeV at CERN SPS exhibits a complex structure of many resonances resting on top of a broad enhancem…
NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (…
Enumerative kernelization is a recent promising at the intersection of parameterized complexity and enumeration algorithms, with two proposed models. The first, known as enum-kernels and due to Creign…
We investigate the Conway--Maxwell multivariate Bernoulli distributions, a family of multivariate Bernoulli distributions derived from the Conway--Maxwell-binomial distribution. We show that it is pos…
Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-compu…
The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based on the Kolmogorov-Ar…
In this paper, numerical simulations of four-mode continuous-variable cluster states with different topologies in the framework of measurement-based quantum computation are presented. By utilizing the…
Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iterative…
Free open-access publishing with Google Scholar indexing.
Submission Guide →