Pith Number

pith:W5TXDENB

pith:2026:W5TXDENBMIXO2F26MJ3NBRYV7G

not attested not anchored not stored refs resolved

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding

Haoxuan Yu, Ning Qin, Xiao Yang, Yingzhe Ma, Zixin Li

AdaFocus improves long-video accuracy while cutting visual tokens by about 33 times through adaptive preview sampling and on-demand disk retrieval.

arxiv:2605.12954 v1 · 2026-05-13 · cs.CV · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{W5TXDENBMIXO2F26MJ3NBRYV7G}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

AdaFocus delivers a substantially better efficiency-accuracy trade-off than strong baselines. Compared with conventional dense encoding, AdaFocus achieves improved task performance (e.g., +2.59 accuracy on VideoMME, +8.39 mIoU on Charades-STA over single-pass inference) while reducing visual token consumption by ~33x and eliminating the need for in-memory frame pre-caching through its zero-cache disk retrieval design.

C2weakest assumption

The uncertainty-triggered refinement mechanism can reliably identify when and which high-resolution evidence is needed from the initial low-cost preview, without missing critical details that would require exhaustive preloading.

C3one line summary

AdaFocus achieves better accuracy on long-video benchmarks with roughly 33 times fewer visual tokens by combining query-aware adaptive sampling and zero-cache disk-based refinement.

References

33 extracted · 33 resolved · 9 Pith anchors

[1] Lisa Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, and Bryan Russell. 2017. Localizing moments in video with natural language. In Proceedings of the IEEE international confe 2017

[2] Qwen3-VL Technical Report 2025 · arXiv:2511.21631

[3] VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 2024 · arXiv:2406.07476

[4] Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher Ré. 2022. Flashat- tention: Fast and memory-efficient exact attention with io-awareness.Advances in neural information processing systems35 2022

[5] Video-R1: Reinforcing Video Reasoning in MLLMs 2025 · arXiv:2503.21776

Receipt and verification

First computed	2026-05-18T03:09:09.314870Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b7677191a1622eed175e6276d0c715f9ad347ca20e9771c7a8c04eb571bb8d20

Aliases

arxiv: 2605.12954 · arxiv_version: 2605.12954v1 · doi: 10.48550/arxiv.2605.12954 · pith_short_12: W5TXDENBMIXO · pith_short_16: W5TXDENBMIXO2F26 · pith_short_8: W5TXDENB

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/W5TXDENBMIXO2F26MJ3NBRYV7G \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b7677191a1622eed175e6276d0c715f9ad347ca20e9771c7a8c04eb571bb8d20

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0721734a9b04f9ec320b89e48c436ad45051e6b51dca5d0413bbd952de1ab46d",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T03:40:21Z",
    "title_canon_sha256": "b19eb8c9b0772b3c7d646a6b05cf2808298dfc8664910e53fc693adce349ce5c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12954",
    "kind": "arxiv",
    "version": 1
  }
}