Aggregate scores for continual learning algorithms rest on a distribution over task orders that is rarely stated. We formulate algorithm comparison as an expectation over a declared order distribution, which separates training variation from order variation, and apply it to motion forecasting with four road-layout task...
Zirui Li, Yunlong Lin, Haohan Yang et al.· 0 citations
In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a...
Zhixian Li, Xingsong Ye, Yongkun Du et al.· 0 citations
A shared memory that does this for a community, prototyped as a social app, SEAM, which works out how fragments relate, distills knowledge about the group, and replies in a situated and associative way.
Ke-Ru Wang, Michael Xu, Ken Perlin et al.· 0 citations
Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction. We characterize this failure for support-based magnetic Laplacians. Exact identities relate imaginary energy and distance from zero phase to amplitude-weighted reciprocity. Top-$k$...
Dawei Han, Zicheng Wang, Yaoxing Ren et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, so...
FoldScape extends sequence-based structure prediction beyond a single folded endpoint to controllable conformational-ensemble generation across protein folding.
Li-Sheng Zhang, Qing-Song Li, Zi-Nan Xie et al.· 0 citations
Standard spatiotemporal graph convolutional networks need a fixed-size adjacency matrix, coupling model weights to a specific sensor count N; they cannot produce any output at a sensor absent from training. We present OmniST, a topology-invariant forecaster whose computation has zero structural dependency on the number...
LLM-powered semantic queries increasingly combine relational processing with multiple LLM-based operators over unstructured data. Efficiently serving such queries is challenging due to runtime dynamism at two coupled levels. Across queries, dynamic arrivals and heterogeneous resource demands continuously change schedul...
Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models. However, standard LoRA typically assigns a fixed rank profile despite layer- and stage-dependent adaptation needs, while recent adaptive-rank variants often rely on heuristic or first-order signals th...
Sihao Wang, Bozheng Li, Xuemiao Xu et al.· 0 citations
Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out-of-vocabulary expressions that make manual lexicon construction costly and degra...
Rong Chang, Lijing Shi, Zhaoxiang Zang· 0 citations
Disturbances can invalidate the conditions required by a robot's next action even when much of its task program remains useful. A recovery system must therefore choose a response suited to the current state. We present DiMuRe (diagnosis-guided multilevel recovery), a framework for robot-use agents that uses phase-speci...
Renkai Yi, Yuwei Wu, Haoyu Zhang et al.· 0 citations
Large language models (LLMs) increasingly shape recommendations across chatbots, e-commerce, and user-generated content (UGC) platforms, creating demand for Generative Engine Optimization (GEO) to improve item visibility in generated responses. Existing GEO studies are mainly content-centric, optimizing visibility unde...
Runlin Lei, Shiqi Zhang, Xiaokui Xiao et al.· 0 citations
