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。
Material rebinding aims to transfer the material appearance from a reference image while preserving the target object's geometry and identity. Existing methods typically struggle to balance material…
Human sleep is organized into a small number of cycles per night: deep sleep dominates early cycles, REM lengthens toward morning, and light sleep clusters at cycle boundaries. These regularities…
The rapid scaling of large language models (LLMs) has unlocked remarkable capabilities across various domains. However, deploying LLMs on mobile devices remains challenging because of their high…
Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions. Because each response…
Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body. Under progressive disclosure, an LLM router selects skills by name and…
Computing equilibria is a fundamental algorithmic problem in game theory and economics. Although general frameworks are available for proving membership in FIXP, the class capturing exact fixed-point…
Imitation policies inherit the operator's pace, and re-timing the demonstrations to run faster works only until success collapses at two to three times demonstration speed. Recent methods attribute…
Whether a policy shifts domains and, by extension, continues, broadens, narrows, or reverses previous policy is of paramount importance to the study of public policy. We propose Dual-Axis Policy…
Learning-based spectrum monitors adapt online to benign propagation changes, but persistent rogue transmissions can gradually become incorporated into the learned background. Spatially distributed…
We present WeSearch, a unified, model-centric retrieval framework for large-scale, continuously evolving content search. Prevailing methods assign documents fixed hierarchical Semantic IDs,…
Laser doppler vibrometer (LDV) scans can be used to detect defects and cracks in manufactured parts before they are deployed. This work presents a method for reconstructing the steady-state surface…
Modern robot policies often perform expensive inference to generate action chunks, making serving a latency bottleneck for real-time control and a throughput bottleneck for multi-robot serving.…
All-in-one image restoration aims to recover high-quality images from multiple degradation types using a single unified model. Recent methods improve unified restoration with hybrid attention, prompt…
Reinforcement learning (RL) is increasingly used to adapt pretrained vision-language-action models (VLAs). We investigate the problem of behavioral steering: adapting a VLA's execution style to…
LLMs degrade in multi-turn conversation partly because of context pollution: the model's own earlier outputs stay in context and anchor later turns, so an early misreading of the user's intent can…
Large language models (LLMs) are increasingly used in dynamic financial trading, yet real-time trading benchmarks mainly evaluate agents by cumulative returns and risk-adjusted performance. Such…
Most agentic robotic systems use vision-language models (VLMs) either to orchestrate predefined skills or to directly generate actions, constraints, and control programs. The former is limited by the…
Recent years have witnessed the flourishing of self-supervised learning on heterogeneous graphs, e.g., masked autoencoder-based methods. However, existing methods suffer from three issues, including…
We study the comparison of statistical experiments from a decision-theoretic standpoint, working with Markov transitions as basis-free linear maps on dual spaces. Our starting observation is that the…
Wearable robots such as supernumerary robotic limbs (SRLs) can augment human capability, but their effectiveness depends strongly on the operator's sense of embodiment, comprising the sense of agency…
Large language model (LLM) agents are rapidly being integrated into complex professional workflows such as auditing and entrusted with judgments under human review. Human auditors are known to yield…
Answering a complex question about a long video is a grounding problem: the answer turns on a few seconds of evidence, and vision-language models remain well below human accuracy at finding them. The…
Parallel speculative drafters use a lightweight serial head to recover token dependencies within a block generated in parallel. Each head step updates only a small state, yet projects that state…
Decision models such as TypeSafe's Jev answer typed questions about a text (yes/no, multiple choice, or an ordinal score) with calibrated probabilities in a single forward pass and without generating…