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。
Complex information seeking on the Web often requires collecting evidence from multiple documents and reasoning across them, as in multi-hop question answering. Multi-agent systems address such tasks…
Domain generalized semantic segmentation is challenging because it requires accurate dense prediction on unseen domains without any access to target-domain data during training. Existing methods…
Generating interactive 3D assets from a single image requires realistic appearance, fidelity to the depicted object, and plausible physical behavior. Yet detailed geometry alone does not determine…
As language models (LMs) have improved, an increasingly common means of evaluating their linguistic competence is through explicit prompting (e.g., "Which sentence is more acceptable?"). Prior work…
Tokenizers are usually treated as fixed preprocessing tools, but they are trained on text and can retain traces of that text in their vocabularies. We ask whether a BPE tokenizer can reveal if a…
We present an inference-time approach that enhances the visual diversity of image sets generated by text-to-image models, without compromising the average image quality. Our method leverages the…
Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether redundant models permit local…
Learning continuous-time dynamical systems from data is an active area of research. The Koopman formalism is often used here, because it is a flexible approach that is informative about the system's…
Targeted protein degradation (TPD) represents a fundamental shift in drug discovery, moving beyond traditional target inhibition toward the event-driven removal of disease-causing proteins. A…
Distribution Matching Distillation (DMD) distills multi-step diffusion models into few-step generators by minimizing reverse KL divergence. Despite its strong performance, DMD guides samples by local…
Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Knowledge-Atomic,…
Segmentation networks that predict at an output stride are trained against label maps downsampled by strided sampling, nearest-neighbor resampling or majority pooling. These methods label each coarse…
In the context of multi-stage trajectory planning for robotic percutaneous liver interventions, identifying a kinematically feasible entry point remains a critical computational bottleneck. Existing…
We study post-training for dynamically routed mixture-of-experts (MoE) models, focusing on integrating independently optimized specialists while keeping consolidation efficient. Our approach combines…
New concepts based in interactional thinking are required to understand how humans are changed by relating to LLMs. Standard theories of technological impact upon users' autonomy are inadequate here,…
Noise synthesis is commonly approached through physical models of image formation or neural networks trained to generate noisy images. We explore a middle ground: an explicit statistical model fitted…
Prompt-tuning has emerged as a parameter-efficient technique for adapting large-scale vision-language models (VLMs) to downstream tasks while keeping the pre-trained weights frozen. However,…
Automated animal re-identification from photograph sequences can facilitate minimally invasive Capture-Mark-Recapture studies at scale. Yet, photographs taken during an observation session can vary…
Probabilistic meshless methods solve partial differential equations (PDEs) by placing a Gaussian process prior on the solution and conditioning it on the PDE at a finite set of collocation nodes. The…
Large Language Models (LLMs) rely on Multi-Head Attention (MHA) for sequence modeling, but scaling to long contexts is constrained by the quadratic cost of attention, motivating sub-quadratic…
KV cache quantization is well studied for autoregressive language models, where cached prefix states are exact under causal attention and quantization is mainly a cache reconstruction problem.…
Unlike autoregressive large language models (AR-LLMs), diffusion LLMs (dLLMs) generate text by iteratively denoising many tokens in parallel, offering a promising path to efficient inference.…
LiDAR-based 3D perception underpins autonomous driving and robotics, yet deploying these models safely requires stress-testing them against adversarial inputs before real-world use. Although…
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs the model finds least predictable. This rule is unsafe when the stream contains…