arXiv AI
Jul 28
CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion
arXiv:2607. 23159v1 Announce Type: new Abstract: Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more.
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.
Related stories
arXiv AI
Aug 25
ReWorld: An Interactive World Model with Long-Horizon Memory
arXiv:2608.23565v1 Announce Type: new Abstract: An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: contro...
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.
Hugging Face Trending Papers
Aug 24
ReWorld: An Interactive World Model with Long-Horizon Memory
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounde...
arXiv AI
Aug 18
SCOPE: Score-Isolated Agentic Optimization for Video World Models
arXiv:2608. 15043v1 Announce Type: new Abstract: Video world models are increasingly used as simulators for planning and embodied decision making, yet improving them at inference time introduces a subtle evaluation problem: prompts, samplers, verifiers, and selectors may evolve together, making it difficult to attribute gains or prevent held-out feedback from shaping the final policy.
arXiv AI
Sep 3
Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation
The paper introduces a sparse, residual world model that focuses on predicting only the changes in a scene by using a per-object change gate and a residual delta head. On a MuJoCo tabletop pushing benchmark, this approach outperforms a dense multilayer perceptron, achieving 2.5 to 4.6 times better next‑state pose accuracy with 8.6 to 11.1 times fewer parameters, maintaining high change‑detection F1 scores, and showing strong transfer across object counts. In autoregressive rollout and sampling‑based planning, the sparse model accumulates less error and enables successful planning where dense models fail.
Hugging Face Trending Papers
Jul 21
Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream
Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model.
arXiv Machine Learning
Aug 12
The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.
arXiv Computer Vision
Aug 26
GlanceWAM: Sparse Test-Time Imagination for World-Action Models
GlanceWAM introduces a sparse test‑time imagination approach for world‑action models that decouples visual imagination from control. By asynchronously generating a single lookahead frame on a slow clock and decoding action chunks at a 48 ms control rate purely in latent space, it avoids latency while maintaining high success. The method achieves 72.2 % on the RoboCasa kitchen benchmark and 99.0 % on LIBERO, running 24× faster than synchronous baselines.
arXiv Machine Learning
Jul 23
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
arXiv:2607. 20125v1 Announce Type: cross Abstract: Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attention the dominant inference cost, especially at high resolution where each frame contributes many tokens.
arXiv AI
Jun 11
Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining
arXiv:2606. 11387v1 Announce Type: cross Abstract: Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets.
arXiv Machine Learning
1d ago
The Decision Value of Perception Compute
arXiv:2609.35910v1 Announce Type: new Abstract: Adaptive perception spends extra computation on inputs where perception is expected to improve. When perception feeds a downstream decision system, a b...