AI Research & Papers

Large language models (LLMs) on personal devices keep user data local, but limited memory restricts their general capability. Since most user-specific tasks do not require the breadth of frontier models, a practical solution is to adapt a …

Expert offloading enables large mixture-of-experts (MoE) language models to run locally, but conventional batching stalls the GPU while missing experts are fetched. A popular remedy, known as prefetching, is to predict what experts will be…

Reinforcement learning objectives that maximize expected return can concentrate probability mass on a small subset of high-reward outcomes, limiting diversity when multiple distinct solutions are desirable. We introduce Density-Aware Rewar…

Reinforcement learning with verifiable rewards (RLVR) has become an effective approach for improving mathematical reasoning in large language models. However, a fundamental question remains: when a model fails to solve a problem, does it t…

Large language models are candidates for collecting and analyzing records in criminal investigations and mass surveillance. Their capability and accuracy in this work cannot currently be measured. Real deployments lack the ground truth nee…

SAE-based feature-level interventions to suppress PII leakage in LLMs are primarily evaluated by log-probability reduction. We show that this criterion cannot distinguish feature specific suppression from a magnitude artifact: a direction-…

In single-pixel (ghost) imaging, known illumination patterns probe an object and a detector with no spatial resolution returns one number per pattern. Each measurement costs acquisition time and photons and, for ionizing probes, contribute…

Split Inference (SI) addresses the hardware resource limitations of Internet of Things (IoT) devices by distributing tiny Machine Learning (TinyML) model segments across multiple IoT devices. However, a device failure can interrupt the inf…

We study cooperative multi-agent reinforcement learning with decoupled dynamics and a monotone submodular reward function over joint trajectories. Due to the non-additive reward, an optimal policy may depend on the history of all agents. T…

A deployed LLM coaching agent answers requests whose correct response depends on player state and game version, so advice that is right for one player can be wrong for the next. We describe TactiNavi, the serving system behind the LLM coac…

Probabilistic time-series forecasting requires models that simultaneously capture structured temporal dynamics, expressive uncertainty, and efficient inference, yet existing approaches fall short of this goal: latent dynamical models impos…

An activation steering edit should depend on the input exactly when the destination varies \emph{inside} the class a query requests, and that is measurable before any rule is fitted or applied. Contrastive Activation Addition (CAA) adds on…

Hybrid models let neural networks supply the unresolved parameters of a process-based simulator, and are fitted to observations that constrain aggregate fluxes and storages but not the internal partitioning that produces them. Such a fit i…

Graph neural network explanations are often evaluated via deletion fidelity, i.e., by deleting their top-ranked edges and measuring the resulting change in model output. Yet, in a message-passing GNN, "deleting an edge" does not specify a …

Transaction event sequences support diverse prediction tasks in online commerce and digital financial services. The same transaction records can yield prediction targets with different semantics, including values, changes, and relations to…

Small multirotor drones produce a characteristic acoustic signature, and microphones offer a low-cost way to detect them. High accuracies have been reported on public drone audio benchmarks, often with random clip-level splits of datasets …

Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. …

Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploi…

Robotics and AI systems are increasingly deploying large vision-language models (LVLMs) to follow high-level instructions, from routine household chores to more complex organizational tasks. Yet, broad directives like "clean the room" or "…

Distributed learning has drawn considerable attention due to its capability of learning from distributed data without aggregating raw observations. However, frequent exchange of model updates can become the main bottleneck of communication…

We study online learning with directed weakly observable feedback graphs and propose a Follow-the-Perturbed-Leader (FTPL) policy that achieves best-of-both-worlds guarantee with nearly linear expected time complexity. To preserve the simpl…

In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images bef…

Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search…

In groups, knowledge is distributed among individuals, and how it is brought together depends on social ties. Taking inspiration from how a single mind recalls and reacts to memories and current stimulus, we build a shared memory that does…

Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction. We characterize this failure for support-based magnetic Laplacians. Exact identities relate imagina…

Data-driven algorithms are ubiquitous across industries, and there is an extensive literature on analyzing their \emph{average} performance. The risk profile of such algorithms, while critical, is much less understood. This paper quantifie…

Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. Whe…

Protein structure predictors reliably identify native conformations, but do not describe the continuum connecting unfolded ensembles to folded states. Here we present FoldScape, a sequence-conditioned deep learning framework that generates…

Discrete diffusion models with parallel decoding are often distilled using token-wise KL objectives. Although token-wise KL exactly matches the corresponding product-form block distributions, its probability-space optimization geometry and…

Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a universally superior harness, we introd…

As deep learning (DL) models become increasingly complex and hardware architectures grow more heterogeneous, DL compilers play a critical role in optimizing computational efficiency and enabling scalable deployment. This paper presents a s…

Digital Twins are evolving from passive virtual representations into closed-loop systems that continuously synchronize with physical assets and drive real-time decisions. Yet predictive modeling, machine learning (ML), uncertainty quantifi…

External text can affect a retrieval-augmented generation (RAG) system only after the retriever admits it to the model context. We stress this admission step while varying document content, attacker query information, per-target poison bud…

Inoculation prompting is a method to reduce undesired behaviours such as reward hacking in frontier models. It works by training a model on harmful examples under a prompt that specifies the undesired behaviour, which reduces the model's t…

Standard spatiotemporal graph convolutional networks need a fixed-size adjacency matrix, coupling model weights to a specific sensor count N; they cannot produce any output at a sensor absent from training. We present OmniST, a topology-in…

Understanding what kind of prompts users typically ask and how well an LLM performs on these prompt categories is crucial for LLM practitioners. The existing methods satisfy the demand by hierarchically clustering the user prompts and synt…

LLM-powered semantic queries increasingly combine relational processing with multiple LLM-based operators over unstructured data. Efficiently serving such queries is challenging due to runtime dynamism at two coupled levels. Across queries…

Video games provide a practical setting for collecting vision-language-action (VLA) data, whose acquisition in physical environments is costly. Existing datasets, however, remain limited by restricted game coverage, sparse language supervi…

Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models. However, standard LoRA typically assigns a fixed rank profile despite layer- and stage-dependent adaptation needs, whil…

Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out…