微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开,或复制链接后用系统浏览器访问。
XMT
短闻
信流 · 上滑连读 · 来源可核
1 / 24
从「3D相册」到「物理底座」:CVPR 2026 开启 3DGS 的具身智能时代
秒级前馈生成、Neural ODE 物理碰撞与真实抗噪建图,3DGS 正演变为机器人模仿学习的数字孪生工厂。作者丨张 璐 编辑丨齐铖湧 在过去两年的 3DGS 研发浪潮中,我们经常看到这样的奇观:算法在论文里跑出了惊艳的 3D 渲染画面,但一拿到真实手机或机器人上,立刻卡成ppt甚至崩溃。…
- “能在实验室发论文”与“能在工业现场干活”之间,隔着一条残酷的工程鸿沟。
- 到了 CVPR 2026,这场画质内卷的狂欢终于踩下了刹车。
- 前沿团队们的视角全面转向工业落地:从秒级前馈生成、GPU 算子重构,到抗噪 SLAM 建图与 Neural ODE 物理碰撞推算,3DGS …
RSS 官方收录 · 可信分层展示
别再乱调图像塔了!浙大 IJCAI 论文揭露 VLM 非对称性真相,给 CLIP 微调「踩刹车」
A3B2自适应非对称适配器,诠释大模型微调的“克制”艺术。作者丨张 璐 编辑丨幸丽娟 在视觉语言大模型(VLM)落地少样本迁移任务时,高效参数微调(PEFT)是大家普遍采用的低成本方案。…
- 然而,业界长期存在一个惯性思维:既然是做图像分类,给图像编码器多挂几个 Adapter、多做微调,模型理应能看懂更多视觉细节。
- 但现实却演化出一个尴尬的矛盾:在面对未知的现实场景(域外数据/OOD)时,在图像编码器上微调得越激进,模型的泛化能力反而破坏得越惨烈。
- 预训练大模型原本拥有一双看懂万物的“好眼睛”,强行局部微调反而把它“改近视了”。
RSS 官方收录 · 可信分层展示
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
arXiv:2608.…
- 13926v1 Announce Type: new Abstract: Large language models have made n…
- Where the consumer cannot inspect the generated query, as in enterpris…
- This is a reliability problem before it is an accuracy problem.
RSS 官方收录 · 可信分层展示
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
arXiv:2608.13921v1 Announce Type: new Abstract: LLM agents increasingly maintain personal memory across sessions, but it can conflict.…
- Preferences depend on context, behavior evolves, and sources can confl…
- When a query lacks context, time, or source authority to interpret con…
- Existing benchmarks recover one answer from conflicting evidence, over…
RSS 官方收录 · 可信分层展示
Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference
arXiv:2608.…
- 13863v1 Announce Type: new Abstract: Deep neural network (DNN) inferen…
- To enable energy-efficient DNN inference, most existing studies focus …
- In this paper, we consider the impact of memory frequency and computin…
RSS 官方收录 · 可信分层展示
MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends
arXiv:2608.…
- 13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test…
- We compare MemoryLake, a structured multi-track memory backend, with M…
- The systems share the same agent framework, requested gpt-5-mini model…
RSS 官方收录 · 可信分层展示
Disney World Officially Announces 'Monsters, Inc.' Themed Land Opening in 2027
SummaryDisney World has officially announced Monstropolis a brand-new 'Monsters Inc.…
- ' themed land coming to Disney's Hollywood StudiosThe expansion will f…
- themed land set to open at Disney's Hollywood Studios in 2027.
- The immersive expansion was unveiled during the D23 convention by Walt…
RSS 官方收录 · 可信分层展示