The paper investigates UAV‑mounted reconfigurable intelligent surface (RIS) assisted device‑to‑device (D2D) communication with stochastic link activation. It models UAV motion, attitude, time‑varying Rician angles, and angle‑dependent RIS reflection, and formulates a joint optimization of UAV trajectory, attitude, and RIS phases to maximize average sum rate under mobility, energy, and hardware constraints. The authors employ deep reinforcement learning and a Decision Transformer trained on expert trajectories from multiple scenarios, showing that zero‑shot transfer outperforms direct DRL transfer and that online fine‑tuning achieves competitive performance with fewer interactions.
By Yaxuan Liu
TeleOCR is a unified framework for document parsing that tackles challenges in both decoupled and end-to-end Vision‑Language Models. It introduces deformation‑aware learning to handle geometric distortions, an adaptive sampling mechanism for complex layouts, and a content‑structure decoupled strategy to model formula grammars and table structures. The approach achieves state‑of‑the‑art results on multiple benchmarks, including top placement in the ICDAR 2026 Sci‑ImageMiner Challenge.
By Peng Cai, Zhaofan Zou, Shifa Liu, Yikun Wang, Jiawei Tang, Kaicheng Yang, Meng Tong, MingKun Jiang, Zhongjiang He, Hao Sun
FastMap is a lightweight two‑stage framework that completes top‑down categorical semantic maps in real time. It first compresses map patches into compact bitwise tokens using a lookup‑free BitVAE, producing a 0.41 GB model that is 3.7× smaller than prior masked‑modeling baselines. A Masked AutoEncoder transformer then reconstructs missing tokens in a single forward pass (0.011 s per map), and an object‑aware masking strategy enables goal‑conditioned generation without extra inference cost. On the Gibson benchmark, FastMap attains 34.10 % mIoU and 45.84 % semantic Success Rate, more than doubling the previous best, and achieves an 83.8 % Success Rate on downstream ObjectNav, the highest among compared navigation methods.
By Yijie Deng, Shuaihang Yuan, Congcong Wen, Hao Huang, Anthony Tzes
The paper presents a framework of formal operations for assembling context in large language model (LLM)-based engineering design, involving modular context units such as policy prompts, reference units with persistence, and user questions with prompt vectoring. It also introduces a formal method for evaluating modelling-as-code LLM outputs, assessing compliance to intent from LLM answers and the support LLMs provide for systems architecture modelling.
By Vinicius Kaster Marini, Petter Krus
RelayS2S is a hybrid real‑time dialogue system that runs a fast duplex speech‑to‑speech path and a slow ASR‑to‑LLM path in parallel. The fast path speculatively drafts a short response prefix and streams it to TTS, while the slow path generates a higher‑quality continuation conditioned on that prefix. A lightweight verifier decides whether to commit the prefix or fall back to the cascaded pipeline, achieving much lower latency (81 ms P90 first‑chunk) while preserving 99% of the cascaded pipeline’s textual quality.
By Long Mai, Junli Liang
LILA (Latent-Informed Layer Analysis) introduces a calibration‑free method for structured pruning of large language models by scoring neuron importance using the Kolmogorov–Smirnov distance between singular value distributions of full and neuron‑ablated feed‑forward network weight matrices. The approach requires no training, calibration data, or auxiliary networks, and outperforms existing methods such as PruneNet and SliceGPT on LLaMA‑2‑7B and Phi‑2 at various sparsity levels. After a single epoch of LoRA fine‑tuning, LILA matches heavily calibrated baselines, and a Neural Tangent Kernel analysis provides theoretical support for its spectral importance criterion. Additionally, LILA can dynamically allocate sparsity budgets, achieving state‑of‑the‑art generative preservation and revealing architectural bottlenecks at higher compression.
By Sankar Behera, Dhruv Singh, Anshika Agnihotri, Raj Kumar Choudhary, Satyadev Ahlawat, Yamuna Prasad
Xiaomi-CocktailASR-1 is an LLM-based end‑to‑end target‑speaker ASR architecture that uses reference speech as voiceprint prompts to transcribe a target speaker directly from mixed audio, eliminating the need for speech separation. It retains competitive single‑speaker performance comparable to mainstream ASR models and introduces a negative sample rejection capability, outputting empty text when the target speaker is absent. The system also supports a Chain‑of‑Thought reasoning mode and achieves state‑of‑the‑art performance on synthetic and real‑world multispeaker benchmarks, effectively addressing the cocktail party problem with a unified architecture.
By Yiru Zhang, Hang Su, Lichun Fan, Ying Zeng, Chang Liu, Yifeng Wang, Yuquan Liang, Tao Li, Lian Li, Wenhao Yang, Jian Luan, Cong Zou, Heng Qu
The paper presents an end‑to‑end pipeline for translating natural language planning descriptions into PDDL problem instances using large language models. It incorporates multiple checks—syntactic parsing, planner success, domain conformance, an LLM critic, and iterative repair—to ensure faithfulness to the original task. Experiments on Planetarium, AutoPlanBench, and curated PDDL~2.1 problems reveal that operational success can diverge from benchmark‑reference reconstruction, and that structured repair improves outcomes while PDDL~2.1 remains challenging for reference reconstruction.
By Joana Rosa, Pedro Santos, Valdemar Oliveira, Rom\~ao Silva, L. Miguel Silveira, Bruno Martins
The paper introduces a multimodal in‑context learning framework that uses contrastive demonstration modeling to align large language models’ responses with the required reasoning paths. By contrasting suboptimal and better responses and incorporating a response‑conditioned retrieval mechanism, the method explicitly guides models beyond surface imitation. Experiments on various multimodal tasks, especially visual question answering, show consistent performance gains.
By Mingbo Yang, Wenqiang Wang, Zhaolu Kang, Peng Chen, Yannan Chen, Sunshang Wang, Yan Xiao
Large language models (LLMs) are increasingly used to assess social bias in text, but the passages they evaluate often contain surface noise such as typos and broken punctuation. This study applied five realistic noise conditions at varying intensities to 3,822 stereotype‑related responses and compared bias judgments on noisy versus original text. The findings show that noise disproportionately turns neutral judgments into biased ones—up to 120 times more likely—while rarely converting biased judgments into neutral ones, and that the most fragile LLM judge exhibits the greatest distortion at mild noise levels. As LLMs become more robust, the bias distortion tends toward parity rather than reversal, meaning bias measured on noisy text is systematically overestimated, especially in fairness‑critical categories.
By DongHyun Ryu, Jaehyeok Lee, YeongJun Hwang, JinYeong Bak
The paper introduces the Discovery Certification Protocol (DCP), a framework that transforms claims from AI research agents into executable tests for recovery and feedback. DCP includes multiple gates that validate improvements, provide controlled information, and measure the impact of truthful feedback, while its core requires strict controls and finite‑sample bounds. Controlled audits in SQLite optimization and virtual catalyst control demonstrated zero recoveries across 96 episodes, with rigorous verification by a deterministic, LLM‑free verifier.
By Jingjie Ning, Shanshan Zhong, Xiaochuan Li, Ji Zeng
The paper introduces a subgroup-targeted membership inference game to audit differentially private synthetic text releases, revealing that existing average-case attacks miss significant leakage to vulnerable subgroups. An extensive audit across 32 proxies, four datasets, three generation methods, and five privacy budgets shows that DP reduces overall leakage but leaves concentrated, uneven residual risk, especially for high-risk records. The study demonstrates that which records leak is determined by the release mechanism rather than the records themselves, challenging record-level risk assessment.
By Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Siew Kei Lam, Anil Anthony Bharath
BiHDTrans is a neurosymbolic binary hyperdimensional transformer that merges self‑attention with hyperdimensional computing to classify multivariate time series efficiently. It surpasses existing HD models by at least 14.47% and binary transformers by 6.67% on average, while an FPGA‑accelerated implementation reduces inference latency 39.4× compared to state‑of‑the‑art binary transformers. Even with a 64% reduction in hyperspace dimensionality, BiHDTrans remains competitive, achieving 1–2% higher accuracy with 4.4× smaller model size and nearly 50% lower latency than the full‑dimensional baseline.
By Jingtao Zhang, Yi Liu, Qi Shen, Changhong Wang
The paper introduces RESCUE-BENCH, a benchmark for relation-aware multi‑party emotional support conversation systems. It is built from real couple and family interview data, comprising 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video, and defines six tasks that assess relational understanding and relation‑sensitive support. Experiments with ten large language models show that while they handle local emotional cues reasonably well, they struggle with tasks that require modeling interpersonal relations, such as predicting relation patterns, viewpoints, and support strategies.
By Haichuan Hu, Yang Xiao, Mingni Tang, Jiawen Duan, Quanjun Zhang, Congqing He, Hao Zhang, Jiashuo Wang, Johan F. Hoorn, Wenjie Li
The paper introduces a phase‑decoupled, model‑calibrated power controller for disaggregated large‑language‑model (LLM) serving, addressing the mismatch between GPU power settings and the distinct hardware regimes of prefill and decode stages. By calibrating separate power caps for each lane based on measured throughput‑latency cliffs, the authors achieve a 20.4% increase in tokens per joule with only a 3.5% rise in mean end‑to‑end latency on an 8‑node B200 cluster, outperforming NVIDIA’s Max‑Q profile. The approach also demonstrates consistent meeting of ITL‑p99 service‑level objectives across multiple MoE models and yields a 32.3% electricity savings over a sustained three‑day run.
By Jae Gon Kim, Donghoon Yoo, Hanyul Ryu, Sungho Ha, Juyeon Lee, Soojung Ryu
The paper introduces EXYGEN, a framework that enables conversational access to large knowledge graphs by combining VoID descriptions, ShEx schemas, retrieved triples, and example question‑query pairs in a retrieval‑augmented generation pipeline. On the SciQA benchmark, this approach achieves an exact‑match score of 0.419 without fine‑tuning any large language model, and shows that larger general‑purpose LLMs can outperform smaller code‑specialized ones when provided sufficient context. To scale metadata generation for very large KGs, the authors propose a predicate‑coverage‑aware parallel graph sampling strategy that preserves structural diversity, reduces runtime by over 80× on OpenCitations Meta and GESIS, and is the only tractable method for obtaining complete metadata on ORKG.
By Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello
The paper presents a method for generating synthetic plankton images conditioned on taxonomic labels to address the long‑tailed nature of automated plankton imaging datasets. A CLIP encoder is fine‑tuned on a large plankton corpus using a ranked contrastive objective that accommodates deep, ragged taxonomies, and then frozen to guide a parameter‑efficient diffusion transformer. The quality of the synthetic samples is evaluated both for distributional fidelity and for their usefulness in training downstream classifiers.
By Daniela Ivanova, Ozgu Goksu, Nicolas Pugeault
The paper presents py‑kvcache, a new KV offload connector for vLLM that uses asynchronous direct I/O, bounded shared staging, and scheduler‑aware preloading to improve external KV caching performance on NVMe SSDs. Experiments across synthetic workloads, long‑context benchmarks, and production traces show that py‑kvcache can load 80k‑token prefixes 2.0× faster than LMCache, with preloading contributing an additional 1.34× speedup, and achieves overall performance within 4% of native vLLM KV Offload. The study highlights that cache effectiveness depends on transfer granularity, intermediate memory use, and scheduling timing rather than just device bandwidth, indicating that external KV caching should be considered a setup‑specific admission decision.
By Joseph Kanichai, Tiziano De Matteis, Animesh Trivedi
The paper presents a prompt-based method for minimal-edit grammatical error correction (GEC) that reduces overcorrection in large language models (LLMs). It introduces taxonomy-based instructions, batch prompting to regularize overcorrection, and LLM-assisted prompt optimization, achieving an $F_{0.5}$ score of 78.32 on BEA-2019 with Gemini 3.1-Pro. This approach narrows the performance gap to fine-tuned models while avoiding their infrastructure demands.
By Kateryna Karpo, Artem Chernodub
The paper presents a method called Positional Task Conditioning (PTC) to improve defect detection in large product catalogs. By breaking detection into focused sub‑tasks and reinforcing task identity at prompt boundaries, PTC reduces context length and isolates error types, boosting F1 scores from 52% to 87%. The approach outperforms rationale‑based distillation across multiple models, achieving near‑state‑of‑the‑art performance at up to 98% lower cost and is deployed in several countries handling over 10 million product families.
By Soham Satyadharma, Gabriel Roccabruna, Suleiman A. Khan