Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as retrieval oriented geo-analytic tasks cannot be supported reliably without first identifying the necessary datasets and constraints. GeoFitBenc...
Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harnes...
Yu-Xin Xiao, Zhi-Yun Lu, Jian-Yu Wang et al.· 0 citations
We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conventional RAG systems, relying on static Knowledge Bases (KBs), our proposal addresses settings where the KB is initially empty and is progressively populated through huma...
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model depth. Existing approaches such as Multi-Query Attention (MQA), Grouped-Query Attention (GQA), Multi-Head Latent Attention (MLA), and Tensor P...
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single terminal behavior. However, this single-point backdoor activation does not explore attacks in which malicious behavior develops gradually through multiple intermediate st...
Tahmid Imtiaz Imu, Emama Nahid, Prodipta Sen Amartya et al.· 0 citations
The results support pretrained TimesFM as a strong initial forecasting baseline for this building, with XGBoost as a competitive locally fitted alternative as a competitive locally fitted alternative.
A. Vasulkar, S. K. Freire, Arie-Willem de Leeuw et al.· 0 citations
Physics foundation models are an increasingly popular approach for building versatile emulators for spatiotemporal systems. They require tokenisation layers that lift physical field data into a latent representation suitable for dynamic processing. A typical choice for this layer is a convolutional encoder, which lifts...
Georg Maierhofer, Miles Cranmer, Payel Mukhopadhyay· 0 citations
Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows that language models can supplement this limited evidence by generating useful replay wi...
Dongkyu Cho, Rumi Chunara, Ali Behrouz· 0 citations
Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens f...
Shu Ishida, Aliasghar Khani, Tianyu Zhang et al.· 0 citations
A greedy, density-scaled composition algorithm is proposed that overcomes limitations of previous attempts to compose circuits by naive union, then generalize it to $N$ circuits via CircuitTree, a new data structure built on a $\Theta(N\log N)$ tree-compose schedule.
Sensing-aided beam prediction can reduce the beam-training overhead of millimeter-wave (mmWave) systems by leveraging environmental information from complementary modalities such as vision and position. However, the resulting sensing and inference pipeline can be energy-intensive, motivating the use of energy-efficient...
N. Nguyen, Phuong Nam Tran, Meng-Yuan Ma et al.· 0 citations
Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) fe...
