跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1865新增论文
+1473其中 AI 相关
+176已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 17:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 18:10 — 2026-11-17 18:10(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 17:12库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,692 已收录论文21,414 AI 相关7,613 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 170 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.21584

CertiSum: Bitwise-Identical MXFP4 Training Across Platforms and Parallelism Layouts

Steve Rhyner, Yubo Gao, Stefan de Lasa, Sankeerth Durvasula, Nandita Vijaykumar

原文摘要

Training with MXFP4, a 4-bit microscaling format, is non-deterministic: identical inputs can produce different results across parallelism layouts and GPU vendors. These differences complicate debugging and training audits and can cause training and inference engines to disagree. We present CertiSum to make MXFP4 training bitwise invariant across runs, parallelism layouts, and GPU vendors. Its key insight is that native FP32 accumulation of MXFP4 products is often already exact for every summation order. CertiSum collects statistics during quantization to certify native matrix multiplication results, recomputes uncertified outputs exactly, and uses exact kernels directly where certification rarely succeeds. CertiSum keeps quantization blocks unchanged across layouts and merges partial sums without rounding, including in attention and weight-gradient computation. In 200-step Qwen3-8B-Base experiments, CertiSum preserves training states bit for bit across AMD MI350X and NVIDIA GB200 and across changes in data, tensor, and context parallelism on MI350X. Across three 8B--14B models on FineWeb-Edu using MI350X, it adds 11.8--60.5% to training-step latency relative to its non-exact MXFP4 counterpart at the larger evaluated input shapes, with speedups of up to $1.24\times$ over BF16 and $1.70\times$ over deterministic BF16.

cs.LG · cs.DC

版本更新 · v2arXiv:2611.03330

The SIMPLE Law for Energy Cost of LLM Inference

Hiari Pizzini Cavagna, Andrea Proia, Daniele Cesarini, Zeynep Kiziltan, Andrea Bartolini

原文摘要

Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along a sequence whose tokens look identical. No analytical model states what a token costs without per-LLM fitting, and no law names the factors that set it. From closed-form expressions of LLM inference's computational and memory-access complexity, we derive the SIMPLE Inference Model to Predict LLMs Energy (SIMPLE), a four-parameter law that separates prefill from decode, and decode into KV-cache and next-token computation cost. Over traces of 13 dense LLMs from several families on NVIDIA H100 GPUs, it attains R2 = 0.969 and 11.97% MAPE, 3.1-3.5x below the SOTA, without per-LLM calibration. SIMPLE explains as well as predicts: prefill energy grows quadratically with hidden dimension, so larger LLMs suffer most from long inputs; and higher GQA KV grouping reduces the per-token energy linearly relative to standard MHA. Increasing the reasoning token budget pushes output length beyond the analytically derived energy minimum, driving super-linear energy growth; accuracy rises but energy rises faster, so Intelligence per Joule peaks at an intermediate budget and falls by up to 3.14x across a 4.0x range. Moving to agentic serving raises energy per request by 13.0x, as both prefill and KV-cache terms grow with input length; prefix caching removes most of the prefill cost (-93%), but not KV-cache cost, so even a cached agentic request costs 4.8x more.

cs.AI · cs.LG · cs.PF

新论文 · v1arXiv:2611.20864

LiDSeg: Linear DehazeFormer Guidance for Efficient Semantic Segmentation in Adverse Weather Conditions

Yobsan Bayisa Leta, Christos Kyrkou, Maria K. Michael, Theocharis Theocharides

原文摘要

Robust semantic segmentation in adverse weather is essential for safety-critical autonomous systems. Existing restore-then-segment pipelines introduce latency and prioritize pixel-level restoration over semantic discriminability, while domain adaptation methods often face representation bottlenecks and computational complexity. We introduce LiDSeg, a framework that uses reconstruction-informed guidance to improve segmentation under adverse weather. During training, a lightweight guidance encoder is jointly optimized with the segmentation branch using segmentation and auxiliary reconstruction objectives. At inference, the reconstruction decoder is discarded, while the guidance encoder is retained to extract weather-robust features. A lightweight gated fusion module integrates these features into the segmentation branch, preserving clear-weather accuracy while improving adverse-weather robustness. On Foggy Cityscapes, LiDSeg limits the clear-to-dense-fog mIoU degradation to 2.5-2.8 percentage points, reducing the baseline performance drop by more than fivefold. On the official ACDC test server, LiDSeg-PIDNet achieves 75.07% pooled all-condition mIoU, comparable to supervised HRNet-W48 at 75.0%, while remaining substantially smaller. The gains generalize zero-shot to Foggy Driving and Foggy Zurich without training on real-fog images. LiDSeg adds only 1.9-3.1M parameters across several models, with total model sizes of 5.2-39.5M parameters and no inference-time reconstruction overhead. It delivers real-time inference on the NVIDIA Jetson AGX Orin. Code: https://github.com/yobsanb/LiDSeg

cs.CV

新论文 · v1arXiv:2611.20771

Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents

NVIDIA, :, Adi Margolin, Aditya Malte, Aishwarya Chhabra, Alex Hodson, Ameya Sunil Mahabaleshwarkar, Ambrish Dantrey 等 113 位作者

原文摘要

We introduce Nemotron 3.5 Bolt E4B 4GB, an open and efficient small language model further post-trained from Gemma-4-E4B-it and optimized for speed and intelligence per GB of memory used for fast conversational agents. The model carries forward Gemma's strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast, local voice/device assistants, interactive personas, and embedded/Edge interfaces. The model combines natural conversation with multi-turn agentic capabilities to power voice/device assistants, interactive characters and robotic/IoT interfaces running on GeForce RTX, Jetson, and RTX/DGX Spark. Experiments on 21 benchmarks show that Nemotron 3.5 Bolt E4B 4GB achieves the highest average accuracy while generating the fewest output tokens in both reasoning and non-reasoning modes, compared with Gemma-4-E4B-it and Qwen3.5-4B. The model is released with a DFlash drafter. With DFlash, Bolt E4B achieves $2.74\times$ the per-user decode speed of inference without speculative decoding at concurrency~1, and $1.21\times$ the generation throughput of Gemma-4-E4B-it with MTP at batch size 1.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2609.06635

From JPEG to CUDA Batch: Measuring RGB Input Pipeline Throughput

Vladimir Iglovikov

原文摘要

We measure how many ready batches per second eight image input pipelines deliver to an NVIDIA L4. Each pipeline starts with RGB JPEG files and delivers synchronized CUDA float16 batches of 256 images. The benchmark contains 1314 measurements across 73 recipes. On the 34 recipes shared by all eight paths, DALI delivered a median of 19.7 batches/s and AlbumentationsX (AX) delivered 17.1. DALI was fastest on 34 of those recipes. Median peak process GPU memory was 1,872 MiB for DALI and 404 MiB for AX.

cs.PF · cs.CV

新论文 · v1arXiv:2611.20289

Benchmarking LLM Inference on Desktop-Scale NVIDIA Grace Blackwell Clusters

Kevin Bhimani, Christian Escobar, Daniel Mihovch, Rudolf Eigenmann, Sunita Chandrasekaran

原文摘要

Two NVIDIA DGX Spark GB10 systems connect directly over 200 GbE to serve larger language models and increase inference capacity, but the benefits depend on how they are deployed. We benchmark 17 open-weight checkpoints spanning dense and mixture-of-experts architectures, 8B to 235B parameters and four weight precisions on one and two RDMA-connected systems. Using vLLM, we compare tensor parallelism (TP=2), pipeline parallelism (PP=2) and a two-replica baseline at concurrency 1 to 64, with three independent launches per configuration. TP=2 delivers a median 1.59x peak-throughput gain over one Spark, versus 1.39x for PP=2 and has higher throughput in 93 of 96 matched comparisons with separated 95% Welch intervals. It reduces unloaded inter-token latency to 0.52x to 0.73x of one Spark, whereas PP=2 provides little reduction. TP=2 also achieves the highest goodput under a strict 100 ms inter-token latency objective wherever both strategies are supported and the objective is met. For models fitting on one Spark, TP=2 generally favors low-concurrency serving, while replication offers higher throughput at high concurrency. One Spark uses less GPU energy per output token at matched concurrency. Across three precision ladders, NVFP4 reduces unloaded latency more than adding a second Spark at BF16. NCCL microbenchmarks and comparisons with an earlier TCP campaign suggest that collective communication overhead contributes to the advantage of TP=2. These results provide deployment guidance for desktop-scale inference.

cs.DC · cs.AI

新论文 · v1arXiv:2611.19922

Lao Siji: Adapting openpilot to Closed-Loop End-to-End Driving in Neural Reconstruction

Chengzhi Gao, Yongzhi Liu, Jinchang Xu, Weichao Zhuang, Guodong Yin

原文摘要

We present Lao Siji, an end-to-end driving policy that ranks third in the 2026 NVIDIA AlpaSim E2E Driving Challenge, ahead of most entries built on foundation models. Instead of training from scratch on a general-purpose vision backbone, we adapt openpilot, an open-source L2 production model. We freeze its vision encoder and fine-tune the policy layers with an ego-state adapter and a route memory. On closed-loop rollouts in neural-reconstructed scenes, we supervise the policy with a privileged map teacher for lateral self-correction and a body-extent loss for road and obstacle clearance, while distilling the base model's remaining outputs to retain car following. Ablations show that self-correction samples carry the gain, while the clearance loss substitutes for them where no teacher exists. Longitudinal safety instead rests on the base model's lead-vehicle estimate behind a rule-based speed layer. Longer training, imitating human logs, and human-log speed targets yield either no measurable gain or adverse effects. Without further training, Lao Siji also places among the leaders on HUGSIM and Odyssey. The final training takes only one GPU-hour and shifts the weights by 3.9% from the shipped model. Code will be released after review.

cs.RO · cs.CV

新论文 · v1arXiv:2611.19512

Sada-ASR: A Production Multidialectal Arabic Speech Recognition System

Mahmoud Khaled, Mohammed Abd-Elnaser, Mahmoud Mohsen, Hazem Ahmed, Abdelrahman Hafez

原文摘要

Callers to Arabic customer-service lines speak their own dialect, while speech recognizers are built and evaluated mainly on Modern Standard Arabic (MSA). A recognizer that mishears the dialect breaks the call before anything else can help. We present Sada-ASR, the speech recognizer of EchoNova's production Arabic voice agent. On a 120-hour test set of MSA and eight dialects, it has the lowest word and character error rates of twelve systems, against eleven from Microsoft, ElevenLabs, Google, OpenAI, Speechmatics, IFM, Cohere, NVIDIA and Audar: 11.69% word error rate against 13.51% for the strongest, Microsoft's MAI-Transcribe-2 (a lead of 0.74 points on clips unaffected by that system's fixed number and script conventions), and 15.52% against 16.96% averaged over varieties. Its largest margins are on Omani (4.30 points), Egyptian (3.78) and Saudi (2.19) speech; it is level on Syrian and loses on Lebanese (24.96% against 23.05%), mostly because it writes Lebanese words in MSA forms and is less verbatim. On six public test sets its average word error rate under the leaderboard's current scoring is 17.17%, below every published figure we found, among them Falcon-ASR (20.92%), Jais-ASR (22.85%) and Audar-ASR-V1-Turbo (23.17%), though none of these states that it used that scoring, so the comparison is indicative. We describe the data pipeline and methodology behind Sada-ASR and release a 20-hour subset of the test set with our scoring code.

cs.CL · cs.SD · eess.AS

新论文 · v1arXiv:2611.19475

StyleJudge: A Human-Validated, In-Context-Learning Vision-Language Evaluator for Artistic Style Transfer

Lokesh, Pramukto Mandal, Somanshu Juneja, Jashnoor Singh, Amit Kumar, Pranav Adlinge, Richa Thakur, Kunal Swami 等 9 位作者

原文摘要

Automatic evaluation of artistic style transfer remains an open problem: existing metrics score an image pair in isolation, without seeing an example of the intended style transformation, and correlate poorly with human judgment. We introduce StyleJudge, a compact vision-language evaluator conditioned on a small set of reference source-to-stylized pairs before scoring a query pair, mirroring how a human rater calibrates to a style before judging a candidate. On a human-annotated benchmark of 878 rated pairs across 12 artistic styles (728 from 10 training/validation styles, 150 from 2 unseen styles), our efficient 0.8B-parameter StyleJudge reaches a Pearson correlation of 0.291 (Spearman 0.325) with human ratings on seen styles and 0.381 on unseen ones. On seen styles, it achieves the highest positive correlation among tested metrics: Gram-matrix style loss and CLIP similarity correlate weakly ($r=0.041$, $r=0.168$), while LPIPS (scored higher when closer to the source) correlates negatively ($r=-0.404$). We achieve this by distilling evaluation knowledge from a 72B-parameter vision-language teacher used only during training, which reaches $r=0.327$, confirming that most of its human alignment survives compact distillation. For training, we build a dataset of source-to-stylized pairs across the 12 styles via LoRA-adapted diffusion, densified with graded intermediate examples from a high-resolution image-morphing pipeline so the evaluator recognizes partial and complete stylization. On two held-out validation styles, StyleJudge reaches 28.2% exact-match agreement with its teacher's structured scores versus 1.1% for the untuned base model, with 67.8% shorter reasoning traces, and scores a pair in 39 s (median) using 2.5 GB of GPU memory on one NVIDIA T4. We release the human-rating benchmark, annotation guideline, SDXL-adapted FreeMorph code, and model weights.

cs.CV

新论文 · v1arXiv:2611.19274

HospitalBench: Diagnosing Where and Why Embodied Agents Fail on Long Hospital Task Chains

Gaytri Jena, Kapil Wanaskar, Aman Chadha, Vasu Sharma, Vinija Jain, Amitava Das

原文摘要

Long-horizon embodied tasks fail in ways that end-task success cannot see. HospitalBench is a diagnostic benchmark of ten hospital chores in NVIDIA Isaac Sim, each two unscored warm-up steps followed by a causal chain of five scored sub-tasks in one continuous simulation: the state one step leaves (an object pose, a choice, a fact seen once) determines what the next step must do, unlike benchmarks that place sub-tasks side by side. Vision-language agents act through skill-level tools from camera images. A scripted robot that makes only the calls a model gets is the solvability check of a chore. From each trajectory the benchmark reads where a chain breaks, what the agent did after a failed call, and how far its own position estimate drifts from the true one. This version reports first results only: 15 of 60 planned runs (three models at high effort, one run each on chores T1 and T10 from both start states and T3 from one), with scripted-robot proofs on three of the ten chores. Of the 15 runs, 2 passed all five sub-tasks. Runs still going after sub-tasks 1 to 5 were 15, 8, 4, 2, 2. Of 189 failed calls, 168 were followed by a different call and 111 by a call that did not fail. These are first results and not a full benchmark. We will release the scenes, task chains, scripted robot, evaluation harness and trajectories.

cs.RO · cs.AI

新论文 · v1arXiv:2611.18145

Compiling Specialized GPU-Initiated Networking

Javid Baydamirli, Ismayil Ismayilov, Kaan Oktay, Didem Unat

原文摘要

Machine learning systems specialize computation to the workload and hardware, but communication remains in generic libraries whose device code and transport decisions are not visible to high-level compilers. We present Obaleth, a compiler that makes GPU-initiated communication part of a kernel's intermediate representation, co-optimizes it alongside computation, and lowers it to specialized transport code. Obaleth plans completions around buffer lifetimes and optimizes memory ordering, synchronization, and batching across NVIDIA and AMD GPUs. On H100 GPUs, Obaleth sends small messages up to 3.3$\times$ faster, and on 256 GPUs runs all-to-all 1.25$\times$ and 2.3$\times$ faster than NVSHMEM and NCCL GIN, with much smaller memory and register use. In vLLM, it serves Qwen3-235B on 16 B200 GPUs and answers requests up to 1.29$\times$ faster than with DeepEP.

cs.DC · cs.LG · cs.PL

版本更新 · v2arXiv:2611.10357

LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages

Felix Fang, Zheng Liu, Robert Saliba

原文摘要

A generative recommender names each candidate with a short token sequence, a Semantic ID, and recommends by generating those tokens. Some generative recommenders, including the Uber Eats search engine we are building, write a whole results page, stores with their menu items, in one decoding pass. Every Semantic ID on such a page must name a real store or item that is eligible for the search, such as a store that delivers to the user's location, and that is not already on the page. Each item must also belong to the store above it. A trie over the catalog keeps identifiers real, but eligibility and repetition change with every request and token, and the grammar-constrained decoder we tried could not enforce these changing rules exactly and quickly. We call this constraint LEGIT, for live eligibility gating over identifier tries. Numbering trie leaves depth first turns each rule into a range lookup over one store trie and one item trie, and every generated page passes an independent catalog check. On one NVIDIA B200 GPU with one or two requests per decode step, a direct implementation that walks the trie on the GPU makes each token about 5 times as slow as unconstrained decoding. Across 36 implementations, hardware counters and ablations are consistent with kernel launches and CPU-GPU waits as the source of this slowdown. Our fastest implementation walks the trie on the CPU while the GPU runs the model, needs no custom kernel, and cuts time per output token by 65.9 percent against the direct GPU implementation, to about 1.7 times the unconstrained cost. This implementation is also the fastest on a page layout that puts each item before its store.

cs.IR · cs.LG · cs.PF

新论文 · v1arXiv:2611.17929

Evaluating Large Language Models for Scientific Paper Search: Retrieval Success and Inference Latency on Mac Studio and NVIDIA A100

Frederic Andriantseheno Rakoto, Yannis Bendi-Ouis, Xavier Hinaut

原文摘要

Scientific literature search can benefit from locally deployed LLM assistants, which reduce reliance on hosted model providers while giving research teams greater control over their data and infrastructure. This work investigates whether open-weight models can support web-assisted paper retrieval under practical computing constraints. We first characterize inference latency as the input context grows from 512 to 128k tokens on a Mac Studio and a server equipped with two NVIDIA A100 GPUs. We then evaluate eight models on the retrieval of 70 papers from seven scientific repositories, using queries that represent three levels of domain knowledge. The results show that retrieval success depends strongly on the selected model and the specificity of the query. And that A100 GPUs are generally faster than the Mac Studio, but its unified memory allows larger models that could not be loaded in the tested GPU configuration.

cs.AI

新论文 · v1arXiv:2611.17867

UltraBERT-JEV: Encoder models for System One Applications

Astarag Mohapatra

原文摘要

We study encoder models that pick one of several options in a single forward pass, without generating text. This technical report compares recipes for fine-tuning UltraBERT-380M with one mask per option. The four recipes differ in how an option is scored and how the scores become probabilities; one follows the expert gate of DeepSeek-V3. Trained on the same data as Qwen3-0.6B with the LLM-as-Jev recipe (67.6% test accuracy), the encoder reaches 69.7% to 72.1%. Scoring an option by "yes" minus "no" instead of "yes" alone gives the larger gain, from 69.7% to 71.3% on the test set and from 57.8% to 59.6% on external benchmarks (56.1% for the decoder). Sigmoid normalisation adds 0.8 test points; a square-root softplus adds none. One request at a time on an NVIDIA A100, the encoder takes 29 ms per decision against 68 ms, but uses more peak memory (2.8 against 2.2 GiB). An auxiliary head, trained on human-marked evidence and on labels selected with a reward adapted from SelfCite, predicts in the same pass the sentences annotated as support for the answer.

cs.CL · cs.AI

版本更新 · v2arXiv:2601.22585

HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs

Heehoon Kim, Chris Jaehwan Lee, Taejeoung Kim, Jongwon Park, Jinpyo Kim, Pyongwon Suh, Ryan H. Choi, Sangwoo Lee 等 9 位作者

原文摘要

The rapid growth of large language models is driving organizations to expand their GPU clusters, often with GPUs from multiple vendors. However, current deep learning frameworks lack support for collective communication across heterogeneous GPUs, leading to inefficiency and higher costs. We present HetCCL, a collective communication library that unifies vendor-specific backends and enables RDMA-based communication across GPUs without requiring driver modifications. HetCCL introduces two novel mechanisms that enable cross-vendor communication while leveraging optimized vendor libraries, NVIDIA NCCL and AMD RCCL. Evaluations on a multi-vendor GPU cluster show that HetCCL matches NCCL and RCCL performance in homogeneous setups while uniquely scaling in heterogeneous environments, enabling practical, high-performance training with both NVIDIA and AMD GPUs without changes to existing deep learning applications.

cs.DC · cs.LG

新论文 · v1arXiv:2611.17565

Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath

Alexander Strack, Marcel Graf, Alexander Van Craen, Dirk Pflüger

原文摘要

Modern multi-vendor GPU environments force a choice between portable code and native performance. GPRat is an open-source Python library for exact Gaussian process regression built on the HPX asynchronous many-task runtime, tiled algorithms, and CPU/CUDA BLAS backends. We contribute a UXL Foundation oneMath backend with a hybrid HPX/SYCL design, extending GPRat to AMD and Intel GPUs. The new SYCL backend comes within 3% of native CUDA on an NVIDIA A30 at the largest problem size and outperforms the GPflow and GPyTorch libraries by up to 1.75x and 2.17x on the A30 and up to 1.79x and 4.62x on an AMD Instinct MI210. On an Intel Arc B580, a consumer-class card with FP64 throughput below our CPUs, the unmodified SYCL backend trails GPRat's CPU backend. Overall, oneMath's dispatch to vendor-native BLAS lets a single SYCL codebase match CUDA on NVIDIA and outperform established Python GP frameworks on AMD, without vendor-specific code.

cs.DC · cs.LG · cs.PF

版本更新 · v2arXiv:2610.02665

大规模语言连续扩散模型

Large Language Continuous Diffusion Models

Zhihan Yang, Wei Guo, Jean-Marie Lemercier, Simon Welker, Mohammad Mahdi Kamani, Yonggan Fu, Sajad Norouzi, Julius Berner 等 17 位作者

AI 速读 基于摘要

提出首个大规模(3B/8B)连续扩散语言模型 Nemotron-Labs-Sigma,通过可操控的低维 ODE/SDE 潜轨迹实现高效推理与加速。

cs.CL · cs.AI · cs.LG

查看原文摘要

Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for reasoning and inference acceleration. To overcome this, we present Nemotron-Labs-Sigma, the first family of large-scale (3B/8B) continuous dLMs built on steerable, low-dimensional ODE/SDE latent trajectories. Trained blockwise via likelihood optimization, Nemotron-Labs-Sigma jointly denoises Gaussian-corrupted token embeddings while learning an optimal embedding geometry, and leverages pretrained autoregressive (AR) weights for warm-starting. At inference, we identify classifier-free guidance and score temperature as essential for high-fidelity reasoning and coding. Against state-of-the-art discrete counterparts (masked dLMs and AR baselines), Nemotron-Labs-Sigma outperforms them on standard benchmarks after pretraining (e.g., GSM8K, Minerva, HumanEval, MBPP) and on challenging reasoning tasks after supervised fine-tuning (e.g., MATH-500, AIME), with the largest consistent gains on coding. Beyond accuracy, we exploit two structural properties unique to continuous dLMs. First, smooth trajectories degrade gracefully at low NFEs and enable efficient few-step distillation: distribution matching proves strongest among the methods we study, giving roughly 8x acceleration on math and 4x on coding (8 and 4 tokens per forward pass) with negligible accuracy loss and preserved diversity. In addition, the one-step speculative decoding on the (pre-SFT) distilled 8B model yields a further ~3.5x throughput gain over the AR counterpart (on GB200), outperforming masked dLM baselines. Second, embedding-space steering controls the quality--diversity trade-off, yielding strong pass@$k$ that keeps improving as $k$ grows. Together, these results establish continuous dLMs as a promising paradigm for efficient language generation.

新论文 · v1arXiv:2611.17212

稀疏卷积的理论与实证分析

Theoretical and Empirical Analysis of Sparse Convolution

Keshvi Tuteja, Yu-Hsiang Tsai, Gregor Olenik, Markus Götz, Achim Streit, Hartwig Anzt, Charlotte Debus

AI 速读 基于摘要

该工作通过roofline分析刻画稀疏权重标准卷积的性能特征,并提出高稀疏度下的高效稀疏卷积技术,初步在NVIDIA A100与Jetson Nano上相对稠密卷积取得加速。

cs.PF · cs.DC · cs.LG

查看原文摘要

Deep neural networks for image processing are increasingly deployed on resource-constrained edge devices such as drones, medical systems, and smartphones, where limited computational resources and memory bandwidth pose significant challenges for efficient inference. Pruning during training often produces highly sparse convolutional kernels, offering the potential to significantly reduce computation and memory requirements. However, exploiting this sparsity efficiently at runtime remains challenging due to irregular memory access patterns and workload imbalance across processing elements. In this work, we investigate the standard convolution with sparse weights and analyze its performance characteristics through roofline analysis, showing that a 3 x 3 sparse convolution achieves an arithmetic intensity of approximately 10 FLOP/byte compared to roughly 96 FLOP/byte for its dense counterpart. We propose techniques for an efficient sparse convolution at high sparsities. Preliminary results demonstrate that our approach achieves upto 1.65x speedup as compared to dense convolution on NVIDIA A100 and upto 1.52x on NVIDIA Jetson Nano (Tegra X1) , motivating further exploration of direct convolution as a practical path to efficient sparse inference on modern accelerators/edge devices.

新论文 · v1arXiv:2611.17152

AeroZoo:面向空气动力学基础模型的良定流动问题基准

AeroZoo: A Benchmark of Well-Posed Flow Problems for Foundation Models of Aerodynamics

Peter Sharpe, Carmelo Gonzales, Corey Adams, Mehdi Ataei, Sanjay Choudhry

AI 速读 基于摘要

作者提出 AeroZoo 基准与训练语料,用 3,815 个 RANS 时均解覆盖多几何族、多外罩配置与宽雷诺数范围,并设计按几何族、外罩、边界条件布局和雷诺数范围留出的冻结划分,以检验空气动力学基础模型的跨分布泛化能力。

cs.LG · cs.CE · physics.flu-dyn

查看原文摘要

Neural surrogates for computational fluid dynamics (CFD) are trained and ranked on datasets that each vary one design family in one flow domain. Such datasets cannot test the least that an aerodynamic foundation model must do: predict CFD-quality incompressible flow in seconds for new shapes in new enclosures. On DrivAerML, larger models and longer training barely lower Transolver's error; doubling the training cases cuts it by about 12% up to 400 cases, exhausting the dataset. We introduce AeroZoo, a benchmark and training corpus of 3,815 time-mean solutions to the unsteady Reynolds-averaged Navier--Stokes (RANS) equations with a transition model, across seven geometry families, eight enclosure configurations and Reynolds numbers from $10^3$ to $10^8$. Each sample poses a well-posed PDE problem in the form a solver receives it: the boundary meshes grouped by condition type, the prescribed values and the fluid properties. The 2,816 samples with a stable time mean form the canonical benchmark: two tasks, engineering metrics and 22 frozen splits, disjoint in geometry, that hold out geometry families, enclosures, boundary-condition layouts and Reynolds ranges. On the random split, boundary-condition tokens cut GeoTransolver's median velocity error from 76.9% to 8.4% of the inlet speed in single-seed runs (uniform inlet flow: 11.0%). ISLA, a transformer for boundary-driven PDEs, reaches 5.3% over four seeds, about 4 times the change from a finer mesh. On the same test samples, a held-out geometry family barely changes ISLA's error relative to uniform flow, and a held-out enclosure or boundary-condition layout raises it 2.4 to 9.2 times. The data and the scoring code will be released.

新论文 · v1arXiv:2611.16856

可持续的LoRA联邦微调:环境影响与性能足迹

Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance Footprint

Pedro Augusto Londe Ribeiro, Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins, Tereza C. Carvalho, Flávio de Oliveira Silva

AI 速读 基于摘要

作者报告在三种GPU上评估联邦LoRA微调的能耗与碳排放,发现本地步数主导能耗变化,较少步数可在保持精度的同时大幅降低能耗。

cs.LG · cs.NI

查看原文摘要

Federated Learning (FL) with Parameter-Efficient Fine-Tuning (PEFT) enables efficient adaptation of Large Language Models (LLMs), yet its energy and carbon costs across hardware remain poorly understood. We evaluated federated Low-Rank Adaptation (LoRA) fine-tuning on NVIDIA A40, RTX 6000 Ada, and A100 GPUs using a $2^2$ full factorial design with 135M/360M models and 10/100 local steps. CodeCarbon tracked energy and estimated CO$_2$-equivalent emissions. Descriptive allocation of variation assigned 84.8-91.2% of energy and emissions variation to local steps within these ranges. On A40 and RTX 6000 Ada, configurations with fewer steps achieved comparable accuracy with roughly 6-8-fold lower energy consumption and higher accuracy per kWh. These findings support smaller local budgets for energy-efficient federated fine-tuning within the evaluated setting.

版本更新 · v2arXiv:2611.09195

InstantHMR : Real-Time Human Mesh Recovery on Your Phone

Mohamed Adjel, Kahina Chalabi, Vincent Bonnet

原文摘要

Real-time 3D human mesh recovery from a single image on mobile devices is a challenging problem with many applications, including robotics, biomechanics, AR/VR, and exergames. Current state-of-the-art models are either too slow to run efficiently on mobile devices or sacrifice accuracy for speed. We present InstantHMR, a family of open-source single-image regressors suited for mobile inference, based on the Momentum Human Rig (MHR) parametric model and trained exclusively on publicly available annotations from the SAM 3D Body dataset. Our approach achieves remarkable performance on a Samsung Galaxy S23 NPU, recovering a 6,890-vertex body mesh in 5.5 ms per person, and 0.98 ms on an NVIDIA RTX 4070 GPU. This speed surpasses all existing methods we evaluated. On mobile, it is 12x faster than the single mobile-compatible method that slightly outperforms ours in accuracy, while achieving competitive accuracy with 40.0 mm PA-MPJPE on 3DPW, 48.8 mm on EMDB and 41.7 mm on RICH. To ensure fair comparisons, we re-evaluate 11 state-of-the-art methods under a unified protocol aligned with the closest MHR-based competitors, including Meta's official MHR-to-SMPL conversion, and report their reproduction results. Additionally, we measure latency across eight different targets, ranging from desktop TensorRT to two phone NPUs. Code and models are available at https://github.com/Naturalpad-studio/InstantHMR.

cs.CV

版本更新 · v3arXiv:2508.02001

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Chungang Lin, Xuying Meng, Tianyu Zuo, Weiyao Zhang, Meng Shen, Ruijie Zhao, Guanming Che, Ruiqi Meng 等 12 位作者

原文摘要

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and vulnerabilities. These pressures have produced two research lines that advance 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, co-achieving versatility and efficiency via such lines has appeared incompatible, with prior work advancing one while compromising the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information often exhibits localized patterns within byte sequences, motivating versatile yet efficient localized byte-sequence modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing strategy that directly embeds raw byte sequences. To maintain versatility across diverse tasks characterized by spatially shifting features, we explore an observation-driven convolution architecture equipped with hardware-friendly scoring and gating designs. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures irrespective of their byte-level offsets. We prototype Nepco on the NVIDIA BlueField-3 SmartNIC with multi-engine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models...

cs.NI · cs.LG

版本更新 · v4arXiv:2606.03159

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling 等 33 位作者

原文摘要

As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures.

cs.CV · cs.AI · cs.RO

新论文 · v1arXiv:2611.16205

QVS-LIVO RiskMap: Health- and Information-Aware View Selection for Multi-Camera LIVO and Off-Road Risk Mapping

Zihan Pan, Jinghan Wang, Hang Li, Feng Cheng, Tianchen Liu, Gaoliang Peng

原文摘要

Multi-camera observations in off-road environments vary significantly in reliability, posing challenges when complementing degraded geometric constraints. Motivated by this, we propose Quality-aware View Selection Lidar-Vision Odometry Risk Mapping (QVS-LIVO RiskMap), which decouples visual processing for state estimation from that for semantic mapping. The front end evaluates camera observations through read-only pretracking on a shared lidar-inertial posterior, combining observation health with geometric complementarity. Channel health memory and switching hysteresis govern selection of at most one eligible view for direct photometric correction. The posterior is retained when no view is eligible or the correction fails acceptance. The mapping back end integrates semantic observations from all available views in a shared world grid. Vehicle-scale geometry constrains semantic risk corrections, while spatial and temporal evidence supports risk confirmation. The system also produces a local bird's-eye-view (BEV) risk map and a global 2.5D semantic-terrain risk map with obstacle instance voxels. On two field sequences, QVS-LIVO achieved horizontal root mean square errors of 0.910 m and 1.664 m. It reduced error by 43.3% relative to FAST-LIO2 on the degraded long-route sequence. Across 12 controlled camera-fault configurations involving dropout, black frames and 60 ms timestamp shifts, it maintained complete trajectories with errors of 1.54-2.23 m. When deployed onboard an NVIDIA Jetson AGX Orin, the system generates local and global maps at 9.94 Hz and 2.00 Hz, respectively, with a median local mapping latency of 32.4 ms. These runtime results demonstrate the real-time feasibility of selective visual state updates alongside multi-view semantic mapping under challenging off-road conditions. The code and related resources are available at: https://github.com/zihanPan-HIT/QVS-LIVO.

cs.RO

版本更新 · v2arXiv:2608.07408

Addressable Memory for Video World Models

Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep

原文摘要

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embedding (RoPE) offsets can exceed the training range and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space degrades memory by averaging keys with incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this cache, WorldTrace uses the model's own attention to decide which observations to retain verbatim and which redundant ones to merge into compressed summaries, all within one bounded addressable memory bank. We evaluate this ability with LoopBench, a benchmark that tests whether a compressed cache can reconstruct a previously visited scene after a long detour. On LoopBench, WorldTrace improves average DINOv2 recall similarity by 32.6% over a sliding window at the same cache budget, extending visually persistent generation without retraining.

cs.CV · cs.LG

版本更新 · v2arXiv:2611.12737

Inference Validation for Regulated AI: A Governed Decision Pipeline for LLM Serving

Dev Akre, Roman Bobalo, Manoj Dobbali

原文摘要

Deploying large language models in regulated industries requires more than picking the fastest inference engine: it requires evidence that a configuration meets contractual and legal obligations before it serves a single customer request. We describe Runway, an internal validation harness built at MasterControl that builds a governed decision pipeline around NVIDIA AIPerf. The key insight is separating concerns: AIPerf provides the trusted measurement, while Runway provides the experiment design that comes before it and the compliance, cost, and audit decisions that come after. We describe the architecture and the storage model that makes caching and audit one mechanism. We report three findings from Runway sweeps: TensorRT-LLM and vLLM rankings invert with concurrency; a newer, pricier GPU instance can be the cheaper one per request; and speculative decoding behaves differently across engines under load, so engine configuration can outweigh engine choice.

cs.SE · cs.LG · cs.PF

版本更新 · v5arXiv:2512.02551

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Songqiao Su, Xiaoya Li, Albert Wang, Guoyin Wang, Jiwei Li, Chris Shum

原文摘要

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execution speed as the RL reward, CUDA-L2 automatically optimizes HGEMM kernels across 1,000 configurations. CUDA-L2 systematically outperforms major matmul baselines to date, from the widely-used torch.matmul to state-of-the-art Nvidia's closed-source libraries, i.e., cuBLAS, cuBLASLt. In offline mode, where kernels are executed consecutively without time intervals, CUDA-L2 yields +22.0% over torch.matmul on average; +19.2% over cuBLAS using the optimal layout configuration (normal-normal NN and transposed-normal TN); +16.8% over cuBLASLt-heuristic, which queries cuBLASLt library and selects the algorithm based on the heuristic's suggestion; and +11.4% over the most competitive cuBLASLt-AutoTuning model, which selects the fastest algorithm from up to 100 candidates from cuBLASLt's suggestions. In server mode, where kernels are executed at random intervals simulating real-time inference, the speedups further increase to +28.7%, +26.0%, +22.4%, and +15.9% for torch.matmul, cuBLAS, cuBLASLt-heuristic, and cuBLASLt-AutoTuning respectively. CUDA-L2 shows that even the most performance-critical, heavily-optimized kernels like HGEMM can be improved through LLM-guided RL automation by systematically exploring configuration spaces at scales impractical for humans. Project and code can be found at github.com/ornith-ai/CUDA-L2

cs.LG · cs.AI

新论文 · v1arXiv:2611.15671

The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models

Aleks Blagojevich, Trevor Sunderland

原文摘要

A quantized model is usually judged by comparing it with its BF16 original, but that comparison changes more than the weights. It often changes the serving engine, it always runs on a different server instance, it may change how requests are batched, and on some stacks the library selects a different kernel depending only on which packages import. We measure each of these sources on the same 2,400 public decisions for two of Cloudflare's decision models, Clef-flash (9B) and Clef (27B), on an NVIDIA GB10, and state every quantization effect as the excess over them. Sources that are not quantization move between 0 and 0.92% of decisions. llama.cpp restarts are bit-identical on every record for both models. vLLM restarts flip 0, 5 and 20 decisions at BF16, FP8 and NVFP4 on Clef-flash and 4, 0 and 22 on Clef; a third instance of Clef's quantized builds (exploratory) leaves FP8 at 0 and puts NVFP4 at 4 to 22, depending on which two instances are compared. An engine change at BF16 flips 6 to 16, a batch-size change 8 to 15, and the Gated DeltaNet kernel transformers selects unasked 10 to 14. Quantization inside one engine moves more: for Clef-flash and Clef, 0.88% and 1.04% at Q8_0, 2.12% and 1.62% at FP8, 5.79% and 3.50% at Q4_K_M, and 5.79% and 5.67% at NVFP4. On both models, every 4-bit interval excludes every non-quantization source. Two of our five pre-registered predictions failed, and the same two fail when the tests are rerun on the 27B: FP8 is not inside restart noise, and changing engine moves fewer decisions than 8-bit quantization does. Accuracy hides most of this. Over the full 31,275 public questions, Clef's Q4_K_M build moves accuracy by a net six questions (-0.02 points [-0.20, +0.16]) while 436 of its decisions get worse (exploratory), and NVFP4 costs Clef-flash 0.95 points and Clef 0.65. We release the code, quantization recipes, per-record outputs and the pre-registration.

cs.LG

新论文 · v1arXiv:2611.15658

Embedded Sim-to-Real Visual Servoing: Learned Reaching and Force-Guided Placement

Dezhi Sun, Duy Khang Banh, Kenan Niu

原文摘要

Embedded perception-to-control systems must combine visual targeting with reliable contact handling under tight computational constraints. We present a shared architecture on an NVIDIA Jetson AGX Orin controlling a Franka Research 3 through Cartesian impedance control. RealSense D435i observations, YOLO11-seg segmentation, depth back-projection, and hand--eye calibration provide metric robot-frame targets. We compare two strategies: compact proximal policy optimization (PPO) policies transferred from simulation for object- and hole-region reaching, and force-guided Cartesian placement using approximately 2 N normal contact and spiral search. The PPO policies achieved 87.2% and 83.1% success over 1000 simulation episodes each. Across 50 real-robot trials per strategy, the learned hybrid and force-guided analytical pipelines achieved 70.0% and 74.0% completion, respectively. Mean perception latency with TensorRT was 34.55 ms. These results support an embedded architecture combining learned free-space reaching with explicit contact correction.

cs.RO

新论文 · v1arXiv:2611.15280

Autonomous Trail Racing with a Bicycle Robot

Fabian Jenelten, Deepana Ishtaweera, Pablo Garcia, Liana Margolese, Igor Bogoslavskyi, Luca Buonocore, Jan Migliazza, Aleksandrs Ecins 等 13 位作者

原文摘要

Navigating off-road trails on a mountain bike requires diverse locomotion skills, including aerial maneuvers, cornering, and slip recovery, paired with sophisticated perception for scene understanding. Translating these capabilities to autonomous, two-wheeled robots remains a formidable challenge. We show that autonomous, high-speed trail navigation can be achieved through a single idea: encoding the trail as a semantic layer of the terrain. In simulation, this layer embeds the navigation task into the training environment; during deployment, it is reconstructed onboard from camera and LiDAR data. First, we introduce a unified learning framework that treats local navigation and locomotion as a joint optimization problem, bypassing the twist or pose command interface of classical control hierarchies. With fixed reward weights, the same framework produces both trail racing and agile parkour, shaped only through terrain semantics and episode length. Second, our perception pipeline combines a frozen vision foundation model with a lightweight dual-head decoder that predicts per-pixel terrain semantics and confidence scores, which are fused with LiDAR range measurements into an egocentric semantic elevation map at 30 Hz onboard an NVIDIA AGX Orin. We validate our framework on the Ultra Mobility Vehicle (UMV), a bicycle robot that autonomously raced across all sections of a kilometer-long, unstructured mountain bike trail at speeds exceeding 5 m/s and averaging 3.26 m/s. In simulation, our policy fails up to an order of magnitude less often than hierarchical baselines while driving faster.

cs.RO