The paper proposes a self‑supervised framework that trains language models to predict concepts—sets of semantically equivalent tokens—rather than single tokens. This approach improves alignment with human similarity judgments, boosts performance on classification, clustering, and reranking tasks, and yields comparable or stronger downstream reasoning while lowering perplexity on semantically meaningful words and only slightly increasing overall perplexity.
By Christine Zhang, Dan Jurafsky, Chen Shani
arXiv:2601.12075v2 Announce Type: replace
Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
By Mehrdad Farahani, Franziska Penzkofer, Richard Johansson
arXiv:2606.03695v2 Announce Type: replace
Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for saf...
By Clara Haya Suslik, Or Shafran, Mor Geva
arXiv:2608.28663v1 Announce Type: new
Abstract: Reliable individual cattle identification supports disease surveillance, vaccination records, breeding management, and livestock insurance. Although th...
By Lalit BC, Dharmendra Singh Chaudhary, Shovit Nepal
arXiv:2608.30003v1 Announce Type: new
Abstract: Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burden...
By Il\'an Carretero, Gustavo Jes\'us Angulo, Roc\'io del Amor, Valery Naranjo
arXiv:2608.30087v1 Announce Type: new
Abstract: Unlearning an identity from a face-conditioned generator by redirecting its conditioning embedding can silently fail if the redirected output is still...
By Zeynel Tok
arXiv:2604.22280v4 Announce Type: replace
Abstract: Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that...
By Peixi Wu, Ke Mei, Feipeng Ma, Bosong Chai, Zhibin Lan, Chenxi Zhao, Shannan Yan, Jie Chen, Zhangchi Hu, Yansong Peng, Bo Lin, Junjie Zhou, Dacheng Yin, Tianyi Wang, Fengyun Rao, Jing Lyu, Hebei Li, Xiaoyan Sun
arXiv:2608.29924v1 Announce Type: cross
Abstract: Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. W...
By Aditi Sarker, Rafi Ibn Sultan, Hui Zhu, Dongxiao Zhu, Prashant Khanduri
arXiv:2608.29748v1 Announce Type: new
Abstract: Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which a...
By Luxi Lin, Zhanpeng Zeng, Shuang Peng, Songwei Liu, Rongrong Ji
arXiv:2607.16862v2 Announce Type: replace
Abstract: LiDAR place recognition supports loop closure, relocalization, and multi-agent map management. As robotic platforms increasingly combine LiDARs wit...
By Nikolaos Stathoulopoulos, George Nikolakopoulos
The paper introduces a GPU‑optimized retrieval framework for LinkedIn’s semantic search, partitioning embeddings into eight category‑supervised segments and applying a min/median aggregation rule aligned with the existing relevance policy. A lightweight Stage‑1 scorer generates high‑recall candidates, while a two‑stage GPU architecture—FP8 coarse ranking followed by FP16 re‑ranking—boosts throughput and recall, achieving 99.6‑99.8% of full‑FP16 recall at over 500 QPS per shard. In A/B testing, the system raises exploratory‑query Precision@10 from 63.7% to 79.0% and navigational Precision@1 from 65.5% to 74.7%, with human evaluation confirming the improvement.
By Dhritiman Das, Chujie Zheng, Ronak Kaoshik, Pratik Dixit, Vishal Shah, Yanbo Li, Jiahao Xu, Manika Agarwal, Chinmay Naik, Lingyu Zhang, Chetan Bhole, Chirag Bhanuprasad Mehta, Meng Zheng, Puneet Singh Ahluwalia, Shirisha Singh, Ping Jin, Manas Apte, Gokulraj Mohanasundaram, Tugrul Bingol, Raghavan Muthuregunathan, Fedor Borisyuk
arXiv:2608.29057v1 Announce Type: new
Abstract: Koopman autoencoders (KAEs) seek a higher-dimensional latent representation in which nonlinear dynamics evolve linearly. However, many interesting syst...
By Aidan Li, Uday Kiran Reddy Tadipatri, Mahan Fathi, Sarath Chandar, Ross Goroshin
The paper investigates when text embeddings can be reliably used as inputs for empirical analysis by formalizing the assumption that embeddings preserve essential information from the original text. Under a generative model where documents are mixtures of latent topics, the author examines two applications: clustering documents in embedding space and using embeddings as controls for high‑dimensional text. Empirical results on 363 U.S. metropolitan areas show that clusters derived from LLM‑generated economic descriptions capture interpretable economic archetypes and better distinguish local employment dynamics than alternative clustering methods or curated covariates.
By Simon Freyaldenhoven
The paper proposes reverse n‑wise output‑oriented testing for AI/ML and quantum computing systems, a method that builds covering arrays over output equivalence classes, confidence buckets, decision boundaries, fairness partitions, embedding clusters, ranking stability bands, quantum measurement distributions, and error syndrome patterns. It then uses gradient‑free metaheuristic optimization to solve the inverse mapping problem, generating input configurations or quantum circuit parameters that trigger specific behavioral signatures in opaque models. The framework claims to provide explicit coverage guarantees, higher fault detection rates for calibration, boundary, and error syndromes, improved test suite efficiency, and automated partition discovery for MLOps and quantum validation pipelines.
By Lamine Rihani
arXiv:2608.30103v1 Announce Type: cross
Abstract: Bilevel mixed-integer linear optimization problems model hierarchical decision processes in which a leader anticipates the optimal response of a foll...
By Jessica D. Elrefaei, Kaixun Hua, Seungbae Kim, Hoang Nam Tran, Juan S. Borrero
The paper introduces CERES, a closed‑loop multimodal indexing framework that addresses semantic collapse in multimodal generation by building a three‑level semantic pyramid and using scale‑routed cross‑attention to generate images that remain retrievable by their original queries. CERES employs a co‑occurrence‑aware router, a lightweight U‑Net generator, and a soft‑Jaccard coverage objective to ensure generated images cover the intended concepts, verified by re‑indexing with a frozen vision‑language model and an external DINOv2 probe. Experiments on four pansharpening benchmarks show state‑of‑the‑art performance, especially under extreme scale variation, and significant improvements in concept‑query retrieval and image‑text ranking metrics.
By Guangyuan Dong, Chuang Liu, Haoyu Wang, Yangchen Zeng, Jiaqi Zhang, Li Jiuxing, Xiaoyang Yu, Pinlong Zhao, Yuchao Hou, Ziwei Li, Zheng Lin, Alexander Lim Han Yang, Yusen Wu
BEACON is a tri‑modal contrastive learning framework that enriches AlphaEarth embeddings by aligning physical representations from Earth‑observation imagery with semantic POI text and human behavioral POI visitation data, while keeping the deployed model image‑only. In a Houston case study, BEACON outperformed six baselines on nine downstream tasks, achieving up to 43% higher R² for obesity prevalence, 34% for poor mental health, and 22% for median household income under a linear probe.
By Hao Tian, Heng Cai, Yifan Yang
arXiv:2604.02194v2 Announce Type: replace-cross
Abstract: Retrieval-Augmented Language Models (RALMs) have shown strong potential in knowledge-intensive tasks, yet they remain vulnerable when retriev...
By Jae O Lee, Jaemin Kim, Sumyeong Ahn, Seo Yeon Park
arXiv:2608.30974v1 Announce Type: cross
Abstract: Joint-Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in la...
By Gabriel Meseguer-Brocal, Yuexuan Kong, Romain Hennequin
AgenticRag‑R1 is a reinforcement‑learning framework that integrates reasoning, retrieval, and memory through a stack and fine‑grained action space. It uses hierarchical action‑aware rewards and an information‑aware trajectory rejection strategy to support long‑horizon learning. Experiments on multi‑hop, open‑domain, and agentic reasoning benchmarks show that AgenticRag‑R1 outperforms strong baselines and produces robust, interpretable, memory‑aware reasoning behaviors.
By Xinke Jiang, Yue Fang, Zhibang Yang, Jiaran Gao, Zhixin Zhang, Tao Feng, Rihong Qiu, Wentao Zhang, Hongxin Ding, Ruizhe Zhang, Yongxin Xu, Yuheng Huang, Xu Chu, Junfeng Zhao, Yasha Wang