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。
Robot agents built on vision-language models depend on both the planner and its harness: the tools, feedback, memory, and recovery logic around it. Can improvements to a large teacher's harness be…
Transformer-based language models have achieved remarkable success in automated short answer grading (ASAG). However, current methods in ASAG struggle to comprehend, reason about and evaluate complex…
Multi-robot systems are increasingly deployed as heterogeneous fleets with diverse kinematic and actuation capabilities. While graph control barrier function (GCBF) methods provide a scalable…
Long-tailed recognition often learns a shared representation before correcting the classifier for class imbalance. Once the classifier has been rebalanced, however, final accuracy does not reveal…
Real-world image editing requires coordinating multiple visual transformations with content preservation and reference constraints, yet aggregate scores can readily obscure unmet local requirements.…
RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy. Restoration-based methods…
Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thousands of images of both nominal and defective…
Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for…
Safe navigation in heterogeneous multi-robot teams faces two coupled challenges: differences in robots' braking and turning capabilities limit how each robot can respond to an approaching neighbor,…
End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust. We apply mechanistic interpretability to E2E driving by…
LLM agents execute tasks through repeated model calls over evolving histories of reasoning, actions, and tool feedback. Aggregate speculative-decoding metrics merge these distinct decisions,…
Stickers are widely used in social media dialogues to express affect, stance, and intent beyond literal text. Their meanings are often non-literal and context-dependent, making them difficult to…
Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop.
Simplicial neural networks (SNNs) are powerful tools for prediction tasks on higher-order relational datasets stored on simplicial complexes (SCs), a higher-order generalization of graphs. However,…
Synthesizing realistic tumors on medical images helps address data scarcity for clinical AI. Existing diffusion-based methods, however, lack fine-grained attribute-level controllability, closed-loop…
Iterative language-model optimizers refine prompts and programs by evaluating a candidate, showing a proposer model a sample of failing cases, and keeping revisions that improve performance. Recent…
Fine-tuning improves a language model's performance in a target domain but can weaken its general capabilities. Existing methods often face a trade-off between general capabilities and domain…
A well-known conjecture in online algorithms is that the (randomized) competitive ratio of online budgeted allocation is $1-1/e$. We refute this conjecture and show that every randomized online…
Learned world models ship as software components whose model versions, preprocessing, and test harnesses change between releases. Work on model updates already counts per-sample regressions, or…
Computer vision models learn hand action only from its visual consequences, without access to the underlying embodied motor signals. We address this absence with MotorSense, the first large-scale…
Vision-language compositionality is the ability to identify which properties, relations, quantities, and states bind to which entities in both an image and a caption, and to match those bindings…
This paper investigates the Women-Are-Wonderful (WaW) effect in language-model blame attribution: a favorable bias in which women receive more positive evaluations than men. Using 11,270…
Rooftop solar potential estimation often relies on LiDAR, digital surface models (DSMs), or pipelines that explicitly reconstruct roof geometry before estimating solar potential. We propose Direct…
This paper presents a neural network model for storing and recalling color images of different sizes using the Cue BallRecall Net systems [1,2,3,4,5]. The Cue Ball system consists of a Recall Net…