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。
LLMs are increasingly used to design heuristics for computer systems. However, most synthesis frameworks evaluate candidates by their average performance, which can mask severe regressions on…
The Deep Linear Network (DLN) is a simple version of a Multilayer Perceptron (MLP) in which the activation function is the identity and the bias vector is the zero vector. We examine the behavior of…
When searching for an object, humans naturally combine semantic intuition - reasoning about where the object is likely to be stored - with geometric awareness of what parts of the space are visible,…
Freezing of gait (FoG) detectors built on inertial measurement units (IMUs) are accurate while the legs move, but they become unreliable when the legs are nearly still, which is exactly when akinetic…
System One decision models replace text generation with typed, probability-scored answers and are entering production. Answers execute without a person in the loop, and no multi-model audit exists on…
We propose a methodology for investigating the differences between natural and synthetic language in a challenging setting: humorous improvisational dialogue. Our experimental setting compares…
LLM-as-a-judge systems often aggregate multiple judges to improve evaluation reliability. However, judge agreement can reflect shared biases toward verbosity, formatting, or fluency rather than the…
Agentic systems are AI-powered technologies capable of autonomous action within digital environments, such as sending emails or making reservations. They are deeply connected to external tools as…
On hardware whose fastest matrix datapath is INT8$\times$INT8, such as the Neural Accelerators of Apple's M5 GPUs, 4-bit weights must become INT8 operands. Existing MXFP4 kernels already map FP4…
Causal discovery is usually evaluated on simulators or on systems whose ground truth follows from physics or design. When it fails on other real data, the failure is attributed to assumptions that…
The absolute trajectory error (ATE) is the standard measure of camera-motion accuracy, from SLAM to feed-forward 3D reconstruction. On the common Sintel protocol, a constant-velocity straight line…
Machine learning can screen far more candidates than can be experimentally validated, creating a need for selection procedures that identify promising candidates while controlling risk before costly…
Land-cover maps classified from wide-area hyperspectral surveys are least reliable along class boundaries and in ambiguous regions, so their errors are spatially structured. We study how this…
Gene-expression classifiers of cancer type are usually developed and validated within one cohort using random splits. Starting from a quality-aware hybrid Boruta selector from earlier work, we…
Evaluating a stochastic AI system often requires many repeated samples per instance, especially for metrics defined over long horizons. Recent work has shown that modeling instance-level success…
With model weights fixed, we measure how much of an entity-replacement response transfers between English factual questions, beyond whether answers change. We add the hidden-state change from two…
Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by…
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought…
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet…
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically…
Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowledge to a decision…
Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers. Conversely, fast policies like VLAs and…
This paper presents TurnTurk-GPT, a text-based turn-taking predictor for Turkish obtained by fine-tuning a Turkish GPT-2 model with the TurnGPT objective on synthetic and real dialogue, and evaluates…
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is…