The paper introduces a resilient remote robotic control framework that couples control and wireless world models using a Joint Embedding Predictive Architecture (JEPA). By learning latent representations from visual observations and radio frequency (RF) data, the system predicts future robot states and wireless conditions to schedule uplink transmissions efficiently. An adaptive resilience mechanism adjusts perception embeddings when prediction errors arise, enabling robust operation without retraining the entire control policy.
By H. P. Madushanka, Sumudu Samarakoon, Mehdi Bennis
The paper presents Test-Time Adaptation via Cache Personalization (TTA‑CaP), a gradient‑free, cache‑based method that personalizes vision‑language models for facial expression recognition in videos. TTA‑CaP uses three complementary caches—a personalized static cache, a positive target cache, and a negative target cache—controlled by a tri‑gate mechanism to prevent corruption and provide robust subject‑matched evidence. Experiments on BioVid, StressID, and BAH datasets show that TTA‑CaP outperforms state‑of‑the‑art test‑time adaptation methods while keeping computational and memory overhead low.
By Masoumeh Sharafi, Muhammad Osama Zeeshan, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger
The paper introduces SEAL, a plug‑and‑play module that enhances single‑image sticker personalization in diffusion models by adding a semantic‑guided spatial attention loss, a split‑merge token strategy, and structure‑aware layer restriction. SEAL integrates without altering the U‑Net backbone and addresses overfitting issues such as visual entanglement and structural rigidity. Alongside SEAL, the authors release StickerBench, a large sticker dataset with six attribute tags to enable systematic evaluation of identity preservation and contextual controllability.
By Changhyun Roh, Yonghyun Jeong, Jonghyun Lee, Chanho Eom, Jihyong Oh
The paper develops a theory for relocating a finite number of compact sets in ℝ^n to arbitrary target domains using diffeomorphisms of ℝ^n. It proves that any such collection can be embedded differentiably into ℝ^{n+1} so that the images become linearly separable. The authors apply this result to show that compact datasets in ℝ^n can be made linearly separable by width‑n deep neural networks with Leaky‑ReLU, ELU, or SELU activations, and that mutually disjoint compact datasets can be separated in ℝ^{n+1} by a width‑(n+1) DNN.
By Xiao-Song Yang, Xuan Zhou, Qi Zhou
The paper introduces a multi‑resolution framework for interpreting human behavioral traces in workplace agents, arguing that a single summary is insufficient. It defines a hierarchy of semantic operators, motifs, episodes, and day‑level rhythms, and applies this to 667 million events from a commercial productivity suite, yielding 120 operator types, thousands of motifs, 25 episode types, and five rhythm archetypes. Validation shows the taxonomy is structurally stable and improves next‑episode prediction by 17% macro‑F1 over a flat baseline, while ablation experiments demonstrate that different questions require different temporal resolutions.
By Lin Ai, Scott Counts
The paper introduces AlleCompanion, a large‑scale retrieval framework for complementary product recommendations at Allegro.com. It addresses the challenge of noisy co‑purchase data by combining data‑level filtering, a category‑constrained Two Tower architecture, and a multi‑source Complementary Categories Mapping (ComCat) that incorporates expert rules, human feedback, LLM reasoning, and statistical mining. Experiments show that these explicit category constraints and neural models effectively reduce noise, improving recommendation relevance and driving significant GMV growth for both organic discovery and sponsored placements.
By Aleksandra Osowska-Kurczab, Klaudia Nazarko, Eli\v{s}ka Kosturov\'a, Lidia Wojciechowska, Micha{\l} Bie\'n
AutoLR is an autonomous harness designed to streamline the iterative research‑and‑engineering cycle for industrial recommender systems, exemplified by NetEase’s gaming‑community app DASHEN. It integrates a multi‑expert council for adversarial review, a deterministic evidence‑weighted selector to allocate trial budgets, and a layered knowledge system that fuses external research with domain‑specific insights and empirical evidence. Large language model agents handle semantic reasoning and code generation, while deterministic controllers maintain control over execution, metrics, guardrails, and state management.
By Qi Zhang, Yanlin Chen, Wenchao Xiao
EyeMakeYou is a multi‑conditional denoising diffusion model that synthesizes high‑frequency, subject‑specific gaze velocity sequences. It conditions on identity, task, and self‑reported subjective states (difficulty, mental tiredness, eye tiredness) to generate realistic 5‑second, 1000‑Hz bivariate gaze data from a reference trajectory. Experiments on the GazeBase dataset show that EyeMakeYou outperforms existing generative methods in spatial accuracy and real‑synthetic similarity while preserving task‑dependent associations with subjective reports.
By Kamrul Hasan, Mehedi Hasan Raju, Oleg V. Komogortsev
The paper introduces Topology-Preserving Adaptive Graph Pooling (TPAGP), a method that partitions graphs into granular balls by combining node features and topology to create multi-granularity representations. TPAGP captures both global and local structural patterns, unlike prior pooling methods that coarsen graphs by removing or clustering nodes. Experiments show TPAGP outperforms existing pooling techniques on benchmark datasets, reducing information loss from fixed-granularity strategies.
By Sen Zhao, Gaojie Xu, Shuyin Xia, Yifan Guan, Yi Liu, Yi Wang, Wei Wang
The paper introduces DEX-Comp, a two‑stage training method for soft context compression in Retrieval‑Augmented Generation (RAG). First, a pure distillation warm‑start trains the compression model on correct responses from an uncompressed RAG. Then, hard exploration uses reinforcement learning on queries where the uncompressed RAG fails, encouraging better computation patterns for compressed representations. Experiments on five open‑domain QA benchmarks show that DEX‑Comp compresses retrieved contexts 16×, speeds inference 4×–24×, and matches or surpasses the uncompressed RAG baseline across various retrieval depths.
By Shuyu Guo, Shuo Zhang, Zhaochun Ren
The paper introduces a multimodal emotion recognition framework that combines audio and visual feature extraction with an attention-based fusion strategy. Audio features include Wav2Vec2 embeddings, MFCCs, and statistical acoustic descriptors, fused via a BiLSTM, while video features are extracted using a ResNet50-BiLSTM architecture. A multi-head attention mechanism fuses these modalities, and experiments on MELD and IEMOCAP show significant accuracy and robustness gains, especially in unbalanced data settings.
By Xu Lin, Ke Wang, Hui Kang, Xinying Wang
The paper reports a comprehensive tuning of both a novel sparse self‑organizing map algorithm (SparseBin) and its baseline cuSPARSE implementation. By optimizing four key levers—tile size, tile‑membership clustering, neuron‑axis chunking, and vectorised loads—the authors achieved a 5.6‑10.1× speed‑up per epoch for map sizes ranging from 32×32 to 512×512, and increased the performance margin over the CUDA baseline from ~80× to ~385×. The tuned kernel saturated the L2 bandwidth at 77% of peak, indicating that further performance gains are unlikely without new hardware or fundamentally different approaches.
By Andrew James Amos
arXiv:2609. 04377v1 Announce Type: new Abstract: Enterprise AI deployments fail not from model inadequacy, but because organizations lack a structured substrate encoding how they decide, negotiate, and execute.
By Fabricio C. Avini, Guilherme Trez
Weather-Conditioned Depth Anything (DA‑W) is a new framework that enhances monocular depth estimation models, like the Depth Anything series, to perform robustly under adverse weather conditions such as fog, rain, snow, and low‑light. It achieves this by disentangling style from content: a Style Filter extracts weather‑specific embeddings from a curated mix of real and synthetic degradation data, which are then injected into the backbone via a lightweight, zero‑initialized adapter. The adapter is trained with pseudo‑label distillation and alignment, enabling a single unified model to adapt to diverse weather scenarios while preserving its generalization on clean data, and it achieves state‑of‑the‑art performance with an average 3.7% improvement in AbsRel on weather benchmarks.
By Zhaoming Xu, Chan-Wei Hu, Kuan-Ru Huang, Zihao Zhu, Renjie Li, Yang Zhou, Zhengzhong Tu
The paper introduces a Neuro‑Symbolic framework that integrates a Vision‑Language Model (VLM) for automatic induction of First‑Order Logic (FOL) rules with a Dynamic Logic Tensor Network (D‑LTN) for differentiable rule verification. In a closed iterative loop, the VLM proposes candidate rules (Think), the D‑LTN verifies them against visual embeddings (Verify), and failures guide the VLM to refine its hypotheses (Revise). Evaluated on the ViSudo‑PC benchmark across four visual domains, the system successfully induces Sudoku constraint rules from only three training examples and achieves AUC scores that match or surpass prior methods such as NeuPSL and LTN.
By Homayoun Afshari, Pietro Basci, Alessandro Russo, Lia Morra
With the widespread applications of large language models (LLMs), privacy-preserving inference has become increasingly essential for sensitive queries. To balance privacy and utility, a series of ligh...
The paper introduces AlleCompanion, a large‑scale retrieval framework used by Allegro.com to improve complementary product recommendations. It tackles the problem of noisy co‑purchase data by applying data‑level filtering, a category‑constrained Two Tower architecture, and a Category Adapter that limits candidates to logically complementary categories. The system also incorporates a multi‑source Complementary Categories Mapping (ComCat) that blends expert rules, human feedback, LLM reasoning, and statistical mining to refine recommendations, resulting in higher GMV for organic discovery and increased revenue from sponsored placements.
arXiv:2609. 03487v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relations into a low-dimensional vector space.
By Junsik Kim, Kangil Kim
FinRAG-QA is a new benchmark dataset for financial question answering, featuring 999 practitioner-curated questions on 10 standardised indicators drawn from 209 annual and Pillar 3 reports of 24 major European and U.S. banks between 2019 and 2023. The dataset focuses on cross‑institutional retrieval over documents averaging 198k words, making it longer than any existing financial QA resource. Experiments on a multi‑stage Retrieval‑Augmented Generation pipeline show that contextual chunk enrichment and a retrieval‑optimised embedding model significantly improve NDCG@10, while a reasoning‑optimised generator boosts answer accuracy from 44.6% to 79.0% when the correct document is retrieved.
By Arianna Miola, Bruno Spaccavento, Lorenzo Silotto, Marco Bianchetti, Luca Cagliero
The paper introduces PACE, a dataset that tests whether personalized assistants can detect hidden conflicts in user requests by integrating implicit, egocentric knowledge from a knowledge base. PACE pairs user requests with persona-specific facts, requiring models to retrieve contextual evidence before deciding if a request is inappropriate. The authors also propose PaceMaker, a multi-agent system that improves conflict detection by coordinating query reformulation, multi-hop graph traversal, and conflict-aware filtering, outperforming existing methods on the PACE benchmark.
By Yoojin Kim, Jihyoung Jang, Hyounghun Kim