New

The companion MPI-extension paper validated the first communication-bearing machine-shape ensemble: four NVIDIA A100 ranks and four CPU ranks on one NCSA Delta node under

Retail recommenders rank relevance, but retailers earn contribution margin: an upsell earns the margin difference over the item it replaces, whereas a cross-sell earns it

Bayesian optimization (BO) over discrete spaces is challenging due to missing gradients and the sparsity of valid solutions. Latent-space BO sidesteps both issues by fitt

Rigid-body motion planning is fundamental to robotic transport and manipulation, where both object position and orientation determine whether a body can move through clut

Benchmarks drive AI progress, but are hampered by task under-specification and over-specification. Task under-specification causes guesswork, where solutions have to make

The physical world has continuous state and action spaces, yet robot planning often benefits from hybrid discrete-continuous formulations that explicitly expose combinato

Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls

Pathology foundation models (FMs) are trained predominantly on hematoxylin and eosin (H&E) images but are increasingly used as frozen feature extractors for immunohistoch

LLM safety evaluations via jailbreaking typically index on attack success rate (ASR): whether a generated response violates safeguards. However, ASR only evaluates sample

Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attrac

Do larger models learn increasingly similar representations of the same world? The Platonic Representation Hypothesis (PRH) predicts that they should, but similar can mea

Multi-human personalization must account for identity changes in people outside the nominal target of a generative operation. We characterize this behavior in UniPortrait

Language models that read financial news are usually trained on text from the same years used to test them, so a backtest can reward hindsight. We build news topics from

Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), video references (e.

Recent Mixture-of-Experts (MoE) approaches address missing modalities either by routing each missingness pattern to a dedicated expert, which scales poorly as the number

In recent years, agentic orchestration has been widely applied to solve complex human tasks. However, existing orchestration learning still faces key challenges, includin

Peer-to-peer collaborative learning is an emerging distributed deep learning paradigm that eliminates the need for a central aggregator and disseminator, avoiding the sin

The way a knowledge graph is serialized as text for inclusion into LLM context can substantially affect downstream LLM performance, with prior work reporting tens of perc

This study examines the transferability of a de-identification model developed for Korean court judgments to a broader range of sensitive documents, focusing on boundary

Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated t

We study the conditional distribution of limit-order volume submitted over the next five minutes, given the current order book and recent order flow. The task requires ca

Distinguishing visually similar characters is a persistent challenge for optical character recognition (OCR) systems, causing errors in critical applications of text digi

Misinformation harms public health and democracy, and generative artificial intelligence now writes falsehoods as persuasive as people's. Defences range from fact-checkin

Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy e

Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external LLM as a monitor, b

Large language model (LLM) unlearning aims to forget certain information while preserving others, without retraining from scratch. SoTA methods such as NPO, SimNPO, and S

High-fidelity 3D generative modeling underpins game asset creation, medical imaging, and VR/AR environmental design, where geometric structure directly influences percept

Large reasoning models solve complex problems through long chains of thought, in which prior work has documented failure modes such as overthinking, underthinking, and un

Developing autonomous electric wheelchairs capable of long-horizon sidewalk navigation is critical for accessible personal mobility, yet existing approaches either focus

Refusal is a common safety mechanism in large language models (LLMs), yet in contexts of suicidal ideation (SI), refusing to engage can itself constitute a safety failure

Augmenting softmax attention with forget gates typically relies on summing decay contributions along the key--query path. Because such accumulation is monotonic, these me

The Long-Range Ising Model benchmark (LRIM) guarantees long-range dependence by construction: each label is the node's spin times the spin field convolved with a power-la

Scalable approaches to learning neural dynamical systems have placed diffusion, flow matching, and few-step generators in flow maps at the forefront of generative modelin

Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchm

Multimodal large language models (MLLMs) offer scalable annotations of social and affective content, but their temporal agreement with human judgments and neural predicti

Runtime query similarity identification supports several activities, including workload analysis, identifying recurring behaviour, auditing, debugging, and anomaly detect

NoveltyScope is a prototype that compares a scientific paper with retrieved prior work and produces a structured report and a five-level novelty score. The system extract

Existing video multimodal large language models (MLLMs) organize observations primarily in time, but embodied spatial reasoning requires organizing them in space. Consequ

Verifier-guided self-repair conditions a model on feedback from failed attempts before it tries again, without weight updates. Yet two findings in prior work are in tensi

We study personalized LLM routing, where a router selects among heterogeneous models with different costs and capabilities. The router must minimize cumulative inference