The growing adoption of digital pathology has rapidly expanded collections of hematoxylin-and-eosin whole-slide images, yet efficient navigation through these archives remains challenging, as metadata is often inconsistent or unavailable. Content-based image retrieval addresses this challenge by identifying similar cas...
Jingsong Liu, Youssef Wally Han Li, Weiwei Zhou et al.· 0 citations
Long-horizon LLM agents make multi-step decisions, yet outcome-reward-only reinforcement learning provides little direct supervision for individual steps. We introduce AttnSR, a step-level reward augmentation method that derives reward allocations from policy attention extracted during training replay, without a separa...
Mengsong Wu, Tianchen Zhou, Zhaochen Su et al.· 0 citations
ZeroRAG is presented, a decentralized routing layer for document retrieval in RAG that performs semantic query routing across an overlay of peers that performs semantic query routing across an overlay of peers with- out global data structures or centralized orchestration.
Petru Neague, Q. Stokkink, Martijn de Vos et al.· 0 citations
Knowledge of the hidden interior structure of an object, including the presence and location of cavities, is essential for predictive simulation, robotic manipulation, and nondestructive inspection. However, such cavities leave no direct signature on the static visible surface, making collision-induced deformation one...
Takuhiro Kaneko· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. In real deployments, however, deletion requests arrive over time, calling for incremental class unlearning (ICU): classes are removed sequentially, previously forgotten knowledge must remain f...
Nicol\'as Segura-Kunsagi, Juan Luis Su\'arez-D\'iaz, Iv\'an Sevillano-Garc\'ia et al.· 0 citations
Tabular Foundation Models (TFMs) adapt to a new task only through the labeled rows in their context. However, labels are expensive to acquire in real-world scenarios due to the need for highly specific domain knowledge to ensure high-quality data. Active in-context learning transfers classical acquisition rules to this...
Vision foundation models are the backbone of modern surgical image analysis, yet most surgical systems still rely on encoders pretrained on natural images or on specialist models trained from scratch on comparatively small datasets. Pretraining encoders on large amounts of surgery-specific data has the potential to gen...
Kun Yuan, Hao Ding, Yi-Qing Shen et al.· 0 citations
Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure. Existing outcome models commonly incorporate these intervention variables into a joint predictor and estimate causal effects through prediction contrasts, leaving the corresponding resp...
Zhirong Huang, Wenzhen Zhang, Guangquan Lu et al.· 0 citations
Deep research agents answer complex questions through repeated search. They rely on a harness that runs their tool calls and returns evidence to their context. This creates a trade-off: Search works best over long passages, which give enough context for reliable semantic matching. But the returned evidence should be sh...
Hoang Tran Vuong, Ngoc Quan Pham, Hung Bui et al.· 0 citations
Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone. Public demonstrations, however, mixed reading raw weights with running code. We separated these conditions in interna...
Masked diffusion models generate text by reversing a stochastic masking process. Unlike autoregressive LLMs, which generate text one token at a time, they can reveal many tokens in parallel, at the price of an error, since tokens revealed together are drawn independently. We show that this trade-off maps onto the stati...
Omni-modal models can answer questions about video, but their predictions rarely show which participant, event, or interval supports an answer. Moreover, answer-level supervision alone does not teach a model to interpret structured video evidence. To systematically mitigate this issue, we present THG-Omni, a human-cent...
Ji-Sheng Dang, Kai-Kai Wei, Ronghao Lin et al.· 0 citations
