← Back to all news
arXiv Computer Vision

Decision-FLIP: Budget-Free Structured Pruning for Gaussian Occupancy Models

Decision‑FLIP is a budget‑free pruning framework for Gaussian occupancy models that scores each persistent Gaussian row by how many voxel decisions change when the row is removed. It uses a guarded Otsu split on the log‑score distribution to select survivors without a target, then compiles the survivors into a smaller checkpoint, reducing bank size and latency. Across multiple model‑dataset settings, the method removes 12–79% of rows, cuts latency by 7–45%, and saves up to 8.0% of whole‑model compute while keeping semantic mIoU within 0.18 points of the original.

Related stories

arXiv Computation and Language
Sep 4

Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs

The study investigates how long‑video language models decide which frames to keep, compress, and reuse, testing each decision in isolation across six selection rules, three benchmarks, and two answering models. It finds that selecting frames based on queries yields the biggest performance boost, that halving spatial resolution costs little, and that reallocating saved tokens to more compressed frames can further improve accuracy. The work also highlights the importance of a unified evaluation harness to avoid misleading comparisons.

By Prakhar Khatri
llmsbenchmarks
More like this →
arXiv Machine Learning
2d ago

Drift Says When, Budget Says How Much: Rate-Controlled KV Re-selection for Long-Form Multimodal Generation

The paper introduces Rate‑Controlled Refresh (RCR), a method for re‑selecting key‑value (KV) cache entries during long‑form multimodal generation. RCR lets attention drift determine when and where to refresh, while a per‑sample controller limits how often this occurs, and a low‑rank drift detector keeps the process GPU‑resident. Across multiple models and tasks, RCR outperforms the per‑step retrieval method InfiniGen by up to 3.8 ROUGE‑L points and remains close to exact per‑step re‑selection, with reduced data movement and a smaller GPU‑resident detector.

By Bin Hu, Yingbo Xiao
llmsefficiencymultimodal
More like this →
arXiv AI
Sep 15

Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models

The paper introduces the Compute-Value Audit (CVA), a sequential framework that evaluates whether extra sampling during test‑time scaling for video world models actually yields a net benefit after accounting for the compute cost of generation and verification. On 192 Physics‑IQ scenes, increasing the sample pool from 4 to 16 candidates improves oracle quality by +9.23 IQ, yet common metrics such as Flow, Cycle, and VideoReward fail to reliably recover this headroom, and adaptive‑depth policies recover only 42‑69% of the potential gain. Only a few specific interventions—anchor‑explorer in a sparse PRM800K setting, MMLU‑Pro exposing a predictive‑state gap, and a privileged paired‑future upper bound—successfully pass all CVA stages, indicating that sampling headroom is valuable only when it can be converted into a reliable decision that survives the full compute charge.

By Yuhua Jiang, Junjie Lu, Feifei Gao
benchmarks
More like this →
arXiv Computer Vision
Sep 14

Beyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation

The paper investigates how much semantic information is lost when frozen foundation models are combined for few‑shot 3D segmentation. By varying the number of retained semantic alternatives before fusion, the authors show that keeping the full distribution of class scores yields higher harmonic‑mean IoU than collapsing to a single class. Experiments on ScanNet200 and ScanNet++ confirm that full‑distribution fusion consistently outperforms top‑1 and other operators, and that most useful information is recovered by retaining a compact set of plausible alternatives.

By Silas Kwabla Gah, Ebenezer Owusu
computer-vision
More like this →
arXiv Machine Learning
Jun 4

LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

arXiv:2606. 04485v1 Announce Type: new Abstract: Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injects value variation through an essentially one-dimensional channel, and feature IDs/positional signals cannot increase within-feature value degrees of freedom, yielding weak early-layer value sensitivity and redundant hidden states.

By Yuanrui Wang, Xingxuan Zhang, Han Yu, Mingchao Ming, Gang Ren, Hao Yuan, Li Mao, Yunjia Zhang, Chun Yuan, Peng Cui
nlpbenchmarks
More like this →
arXiv Computer Vision
Sep 18

Queries Knew More Than We Thought: Uncovering Latent Knowledge in Segmentation Models

The paper investigates an output‑selection bottleneck in frozen DETR‑family segmentation models, showing that many useful mask proposals are computed but never exposed. A lightweight selector called HYDRA, trained only on cached outputs, can recover up to +7.41 mIoU on ADE20k and COCO and +9.4 class‑macro prompt‑IoU on SAM 3 across eight domains by selectively choosing better candidates. The study demonstrates that evaluating segmenters should consider both exposed masks and the hidden candidates they suppress.

By Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Damith Ranasinghe
computer-visionfine-tuning
More like this →