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

+816新增论文
+642其中 AI 相关
+95已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 12:54 — 2026-11-21 12:54(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 4 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2611.00172

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Ziyin Zhang, Yuyu Guo, Ying Zhang, Siqiao Xue, Zihan Liao, Jin Qin, Wenjie Yang, Siyuan Yang 等 18 位作者

原文摘要

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.29643

SemQAM: A Unified Generative Image Codec for Joint Semantic-Channel Coding and Modulation

Hao Cao, Jingkai Ying, Yinhuan Huang, Zhijin Qin, Yuan Shen

原文摘要

Conventional digital image transmission typically optimizes source coding, channel coding, and modulation separately, limiting how source representations adapt to channel impairments. Such impairments can corrupt the latent representations recovered at the receiver and propagate through autoregressive coding, degrading reconstruction quality. We propose SemQAM, a unified generative image codec that supports conventional source coding and joint semantic-channel coding and modulation within a single model. SemQAM represents latent features using vector quantization (VQ), maps the resulting indices to QAM symbols, and updates the codeword selected by the detected index, encouraging easily confused symbols to represent similar latent features. We also use the conditional expectation of received codewords to approximate the receiver reconstruction at the transmitter, reducing error propagation during autoregressive coding without feedback. In the special case of noiseless transmission, SemQAM reduces to a conventional source codec called SemQAM-C. Experiments show that (i) SemQAM-C achieves lower bitrates than OneDC at matched LPIPS and DISTS, with approximately $27\times$ faster decoding. (ii) Compared with the separated SemQAM-C system using LDPC and QAM, SemQAM further achieves BD-CBR savings of 30.85%, 28.06%, and 28.80% on LPIPS, DISTS, and FID, respectively, demonstrating the benefit of joint optimization.

cs.CV

版本更新 · v2arXiv:2610.29691

Efficient Generative Image Compression with Quantized Latents Refinement

Hao Cao, Yinhuan Huang, Wenqi Guo, Yuan Shen, Jungong Han, Zhijin Qin

原文摘要

Generative image compression (GIC) delivers strong perceptual quality. However, GIC methods with strong perceptual quality often rely on pretrained diffusion models with high latency, while recent lightweight GIC methods reduce latency but compromise perceptual quality. At low bitrates, coarse deterministic quantization can map nearby encoder latents representing different fine details to the same quantized point, making those details difficult to recover. Motivated by this, we propose GR-GIC which delivers competitive compression performance with fast inference. For better performance, we introduce Guided Refinement (GR), which combines latent refinement guided by entropy context with adaptive perturbations, jointly improving reconstruction at low bitrates. For fast inference, we introduce reorganized projected residual vector quantization, which equivalently reorganizes residual updates into low-dimensional lookups to expose greater parallelism and reduce latency. Experiments on Kodak show that GR-GIC achieves BD-rate savings of 22.09%, 42.14%, 19.35%, and 30.87% over OneDC for LPIPS, DISTS, PSNR, and FID, respectively. Moreover, our CUDA implementation encodes and decodes in 2.81 and 3.48 ms on an NVIDIA A100, achieving $27.36\times$ and $58.77\times$ speedups over the official OneDC implementation, respectively. We further evaluate GR-GIC on an NVIDIA Jetson Orin NX, demonstrating competitive coding speed on edge hardware.

cs.CV

新论文 · v1arXiv:2611.20455

Embeddings vs. Grep: Rethinking the Dense Advantage in Code Search

Siqiao Xue, Ziyin Zhang, Zihan Liao, Jin Qin, Yixiang Mu, Hang Yu

原文摘要

Code-search benchmarks show dense encoders well ahead of BM25, yet coding agents do well with \texttt{grep}. What does this dense advantage measure? Existing benchmarks cannot tell: they use curated queries, old code and a handicapped BM25. To find out, we build Repo-Premium, a realistic repository-level code-search benchmark. It ranks files in real repositories, with curated and raw queries in Python, JavaScript, TypeScript, Go, Rust and Java, pull requests from 2022 to 2026, and a preregistered test pool over $91$ repositories. Our experiments trace the advantage to two sources: evaluation choices that favor dense retrieval, such as splitting files into chunks for BM25 and counting edited tests as relevant, and queries that lack the code's rare identifiers. Expanding the query with LLM-written identifiers (generate-then-grep) helps BM25 far more than dense retrieval, letting it match dense retrieval in every Python pool, even on pull requests opened after the LLM was released. No method we tried predicts which retriever will win on a given query. From these results we derive three guidelines: measure dense gains against a fair lexical baseline, fuse dense retrieval with BM25, and add the code's words to queries that lack them.

cs.SE