941 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be pulled back to clean-space posteriors with weaker conditioning, with …
Accurate T-staging is crucial for guiding personalized treatment strategies for laryngopharyngeal cancer. However, current clinical practice relies on invasive biopsy procedures, whereas CT-based staging remains challeng…
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fit…
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextua…
Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute ce…
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rul…
Captured human-object interactions provide rich supervision for humanoid loco-manipulation, but they are sparse, heterogeneous, and not directly executable by robots. We introduce InterMimicGen, a self-evolving motion-im…
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting tok…
Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the …
A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original,…
Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum circuit architecture,…
Marine ecosystems are impacted by various threats such as oil spills, algal blooms, and sediment floods, which disrupt habitats, wildlife, and human activities. Advances in satellite imagery and Artificial Intelligence (…
Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to participating clients. However, it does not guarantee that clients submit pol…
Dense-retrieval services must switch among embedding-prefix dimensions and index bit rates as latency, quality, and memory budgets change. Tuning a quantizer separately for each rate gives the best quality, but the retri…
Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies, causing their harmonics to overlap in time-frequency repr…