MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Large language model (LLM)-native advertising has emerged as a viable monetization channel as LLM service providers seek sustainable revenue streams. However, integrating native ads into LLM…
Text-to-image models have achieved remarkable success in generating high-quality images from textual descriptions. However, they often struggle with "semantic drift," where the generated output fails…
Open-source LLMs provide a flexible alternative to closed-source models for Text-to-SQL but still struggle with complex queries. Finetuning with chain-of-thought (CoT) data improves reasoning, yet…
We present \textbf{UniCaMo}, an unified framework for joint control of camera and object motion in image-and-text-to-video diffusion models. Given a reference image, text prompt, sparse 3D object…
AI data analysis today is three fragmented worlds: LLMs understand semantics but cannot compute; BI aggregates precisely but is stateless; ML processes large-scale data on a stateful kernel but lacks…
Virtual metrology (VM) aims to estimate costly or delayed metrology variables from heterogeneous sensor signals and in-line measurements, and it acts as a critical component of semiconductor…
Multi-object image generation in text-to-image diffusion models remains challenging, as existing approaches struggle to reliably generate all objects specified in a prompt. Compositional approaches…
Topology optimization has become an indispensable design tool in the aerospace, automotive, and mechanical engineering industries. Yet bringing a new problem from its description to an optimized…
Diffusion models and more recently Flow models have widespread application. In this work we consider degenerate Diffusion models in which the per-step generator is deterministic.
We study uniform language generation under approximate differential privacy. Given a uniformly bounded number of distinct examples from an unknown target language, a generator must produce infinitely…
Post training for large reasoning models remains insufficient on challenging problems, whose correct trajectories are hard to sample. Though prior works address this difficulty by integrating…
Molecular docking aims to predict the three-dimensional structure of a protein-ligand complex; in the conventional structure-based setting, it is conditioned on an input protein structure and ligand,…
Government agencies use crop maps to estimate production, monitor food security, and set agricultural policy. These crop maps are usually validated against field labels, but these labels are rarely a…
As consumer smartphone recommerce scales, buyers must quote binding repurchase prices from seller-uploaded multi-view photos and diagnostic screenshots before devices reach the warehouse. Accurate…
We study hybrid online learning with stochastic features and adversarial labels when the feature distribution is unknown. Prior work gave stochastic sequential covers of log-size $O(d\log^2 T)$ for a…
Replacing the matrix in an iteration with random low-rank matrices can reduce the cost of matrix-vector multiplication. However, even if the sampled matrices equal the original matrix in expectation,…
Understanding how artificial neural networks (ANNs) represent and combine features internally is a central challenge in mechanistic interpretability. Existing neural circuit-discovery methods…
Vision-language models (VLMs) have shown promise for chest radiograph report generation, but adoption remains limited because of hallucinated findings that are not grounded in the image. Correcting…
Local image--text matching can find strong evidence for individual concepts yet favor captions with incorrect attribute--entity bindings. We introduce ConstraintMatch, a training-free inference…
Calling a tool through generated text adds decoding steps, even when the computation itself is short. We study an alternative: a small neural module that runs inside a language model's forward pass.
Group Relative Policy Optimization (GRPO) estimates advantages against the within-prompt mean reward, a baseline shared across the group. In practice, rollouts within a prompt are not always…
Skeleton-based gait recognition is generally more robust to appearance changes than pixel-based methods, but this robustness depends on stable pose extraction. Clothing variation in gait recognition…
As large language model agents increasingly undertake complex, long-horizon tasks, memory has become an important component for supporting sustained decision-making and action. Existing methods…
Scientific agents make consequential choices about evidence, next actions and research strategy, but choices embedded in generated text are difficult to evaluate independently. Decision-Centric…