Minima-KV introduces a retention‑preserving hierarchy for mixed‑format paged attention that keeps recent and protected anchor pages in FP8 while older pages are compressed into packed TQ3, allowing every live‑request page to remain addressable. The approach uses format‑specific kernels and a globally normalized online‑softmax merge to compute partial attention states, enabling direct heterogeneous decoding without a dense shadow cache. Experiments on Qwen3.6‑27B on a 96‑GB NVIDIA RTX PRO 6000 Blackwell GPU show 3.50× compression over BF16 and 1.75× over FP8, with minimal impact on performance across long‑context benchmarks.
By Sergii Kozyrev (Minima AI, Inc), Davyd Maiboroda (Minima AI, Inc)
The paper introduces IDeaL, a data‑free multi‑teacher distillation technique that generates teacher‑specific, improved samples using decorrelation losses at patch and image levels. By tailoring noise to each teacher, IDeaL produces strong student models that capture complementary teacher information and achieve results close to those distilled from real images. Experiments demonstrate that with only 1,000 images, students trained on IDeaL samples match or exceed the performance of students distilled from a 1,000‑image subset of ImageNet.
By Feyza Yavuz, Mert B\"ulent Sar{\i}y{\i}ld{\i}z, Diane Larlus
arXiv:2608.23744v1 Announce Type: new
Abstract: Split conformal prediction, not the pruning rule, supplies finite-sample marginal coverage once a pruned model is fixed independently of the conformal...
By Ibne Farabi Shihab, Adria Binte Habib, Anuj Sharma
arXiv:2406.17538v4 Announce Type: replace
Abstract: Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is cr...
By Guanghao Zhu, Lin Liu, Yuhao Hu, Haixin Sun, Fang Liu, Xiaohui Du, Ruqian Hao, Juanxiu Liu, Yong Liu, Jing Zhang
The Transformer Accelerator (TFA) is a synthesizable, parameterizable INT8 memory‑to‑memory engine designed for transformer inference and machine translation. It features a one‑time‑multiplexed datapath that handles prompt processing and autoregressive generation, and implements key operations such as matrix multiplication, softmax, RMSNorm, and elementwise functions through eight 512‑bit macro‑op descriptors. In extensive verification, TFA achieved zero mismatches across 25 tests and 34 constrained‑random runs, matched floating‑point references on multiple translation tasks, and delivered a 20× speedup over a 22‑thread CPU while projecting significant energy reductions in larger designs.
By Shashank
QABBA is a quantized variant of the Adaptive Brownian Bridge-based Aggregation (ABBA) method that compresses long numerical time‑series into short symbolic sequences using integer‑quantized symbolic centers. It reduces parameter storage and enables integer arithmetic while providing rigorous error bounds—including a dimension‑free segment error, a time‑domain reconstruction error, a stability condition for symbolic assignment, and a bit‑allocation rule. The resulting symbolic strings can be fed directly into pretrained large language models, and experiments on several benchmark archives show a practical trade‑off among storage, reconstruction accuracy, and downstream predictive performance.
By Erin Carson, Xinye Chen, Fei He, Cheng Kang
Masked diffusion language models (dLLMs) promise faster text generation by denoising multiple tokens simultaneously, yet their real‑world serving behavior has been largely unexamined. Using LLaDA‑8B‑Instruct on a single NVIDIA H200 GPU, the study finds that request difficulty is discretized into 11 step‑count levels, short‑budget benchmarks underestimate serving variance, and only 24% of single‑request time is GPU computation, with batching mainly reducing CPU dispatch overhead. The authors also demonstrate that output quality remains stable across batch sizes and propose a batch‑timeout rule for synchronized batching under Poisson arrivals.
By Farhana Amin, Sabiha Afroz, Mona Moghadampanah, Dimitrios S. Nikolopoulos
PROOF-Gen is a method that improves distillation of tool‑calling models by recovering successful trajectories from teacher failures. It uses per‑scenario prompt optimization to generate corrective guidance that steers the teacher to a passing trajectory, then removes this guidance before training so the student learns from clean demonstrations. On τ2‑bench, PROOF-Gen recovers 93% of failed scenarios, boosting Qwen3‑4B‑Instruct‑2507’s Pass^1 from 0.132 to 0.529 and improving Gemma 4 E4B‑it by 7.2pp on BFCL v4 multi‑turn, while also raising deployed on‑device model performance by up to 5.0pp across response‑quality metrics.
By Anh Ta, Junjie Zhu, Shahin Shayandeh
The paper introduces the "Compression Trinity," a unified framework that jointly applies sparsity, quantization, and low‑rank approximations to compress large language models. It presents several methods—MKOR, SLoPe, OPTIMA, PATCH, and SLiM—that leverage these three pillars to accelerate training, reduce memory bandwidth, and recover accuracy, achieving significant speedups and accuracy gains over existing techniques. The results demonstrate that combining all three compression strategies is essential for efficient, scalable, high‑performance LLM deployment.
By Mohammad Mozaffari
arXiv:2605.30972v2 Announce Type: replace
Abstract: Accurate 3D medical image segmentation requires both fine spatial detail and long-range volumetric context. Although Mamba provides efficient long-...
By Bakht Zada, Chao Tong, Qile Su, Shuai Zhang
The paper presents a strictly causal streaming video anomaly detector that updates a fixed‑size state in constant time per frame, eliminating the need for clip buffering or lookahead. Its core is a diagonal linear state‑space recurrence with a decay gate, trained via self‑supervised next‑embedding prediction on a frozen visual backbone. The authors derive a closed‑form link between the recurrence’s decay spectrum and detection delay, validate on UCSD Ped2 and CUHK Avenue, and report real‑time latency on Apple M3 Pro hardware (≈0.75 ms per frame).
By Yogesh Kumar
arXiv:2304.10041v2 Announce Type: replace
Abstract: This work investigates formal policy synthesis for continuous-state stochastic dynamic systems subject to high-level specifications expressed in li...
By Lening Li, Zhentian Qian, Jianan Xia, Qiren Geng, Huasheng Zhang, Liang Hu, Qishuang Li, Junqiang Lou
arXiv:2608.23879v1 Announce Type: cross
Abstract: Cardiac cine-MRI serves as a direct visual indicator of cardiovascular hemodynamics by capturing the continuous wall motion of the aorta. Quantifying...
By Dexter Wen Jie Teo, Nairouz Shehata, Herve Lombaert
arXiv:2509.18778v2 Announce Type: replace-cross
Abstract: Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly f...
By Shijia Ge, Yijun Liu, Yinxin Zhang, Shuzhao Xie, Weixiang Zhang, Mingcai Zhou, Zhi Wang
SenseShift is an encoder-based framework that enables fine‑grained, sentence‑level sentiment control in text generation. It uses bidirectional attention, quantized sentiment signals, and iterative mask infilling to generate local sentences conditioned on target sentiment intensity. Experiments on story and review generation show that SenseShift delivers stronger sentiment controllability while preserving text quality and robustness to out‑of‑domain inputs compared to larger decoder‑based baselines.
By Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl
ShardMeter is a lightweight analytical performance model that predicts end-to-end runtime for transformer-based workloads across sharded, distributed, and decentralized training setups. By taking a model’s characteristics and a target hardware topology as input, it estimates per-GPU and per-island throughput, training cost, total wall-clock time, and pinpoints performance bottlenecks. The model reveals diminishing-return regimes with increasing island size, quantifies compute- versus communication-bound scaling, evaluates hyperparameter trade-offs, and models cost-throughput for large-scale decentralized training, enabling rapid exploration of configuration space and near-optimal deployment plans.
By Tim Beringer (Technical University of Darmstadt), Patrick Diem (Technical University of Darmstadt), Felix Wolf (Technical University of Darmstadt), Arya Mazaheri (Technical University of Darmstadt, PanocularAI)
The paper proposes a modular training pipeline for zero‑shot cross‑city object detection that combines a multi‑dataset pre‑training strategy with class‑agnostic objectness distillation and a domain‑resilient augmentation stream featuring a Grayworld transformation. Applied to the RF‑DETR detector, the approach reduces cross‑city distribution gaps while using only 16 GB GPU memory, achieving a 24.29‑point mAP improvement and 1st place on the AI City Challenge Track 6 leaderboard. The authors provide code and data at the referenced GitHub repository.
By Long Hoang Pham, Quoc Pham-Nam Ho, Huy-Hung Nguyen, Duong Nguyen-Ngoc Tran, Ngoc Doan-Minh Huynh, Cu Quoc Le, Hoang-Khang Nguyen, Hyung-Min Jeon, Chi Dai Tran, Son Hong Phan, Duong Khac Vu, Trinh Le Ba Khanh, Jae Wook Jeon
arXiv:2608.24650v1 Announce Type: cross
Abstract: System-level simulation is an essential tool for exploring the rapidly expanding design space of LLM serving systems, where real deployments remain c...
By Wonung Kim, Hyunmin Choi, Minsu Kim, Jaehong Cho, Yeongwook Kim, Jongse Park
arXiv:2606.22975v2 Announce Type: replace
Abstract: Text-attributed graphs (TAGs) are widely used in many real-world domains, and learning on TAGs requires jointly modeling text semantics and graph s...
By Yeongho Kim, Yeonje Choi, Kijung Shin
arXiv:2603.00188v2 Announce Type: replace-cross
Abstract: Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing m...
By Bowen Zhou, Zhou Xu, Wanli Li, Jingyu Xiao, Pingan Gan, Haoqian Wang