Pith Number

pith:TIX7TTQH

pith:2026:TIX7TTQHAWJWHZHK6TZD4W5YSF

not attested not anchored not stored refs pending

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Binfei Ji, Brucek Khailany, Kejing Xia, Nicolai Oswald, Pavlo Molchanov, Xinrui Zhong, Yingyan Lin, Yonggan Fu, Zhenbang Du

R²-dLLM reduces diffusion LLM decoding steps by up to 75 percent by removing spatial and temporal redundancies during parallel token generation.

arxiv:2604.18995 v2 · 2026-04-21 · cs.CL · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TIX7TTQHAWJWHZHK6TZD4W5YSF}

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

Experiments demonstrate that R²-dLLM consistently reduces the number of decoding steps by up to 75% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks.

C2weakest assumption

That the observed patterns of spatial redundancy from confidence clusters and positional ambiguity, plus temporal redundancy from remasking stabilized predictions, are general across dLLM models and tasks, and that the proposed aggregation rules plus redundancy-aware SFT can exploit them without quality loss.

C3one line summary

R²-dLLM reduces dLLM decoding steps by up to 75% via spatio-temporal redundancy reduction while keeping generation quality competitive.

Receipt and verification

First computed	2026-06-03T01:05:13.923071Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9a2ff9ce07059363e4eaf4f23e5bb891453b19464d9b8df1d190511e061e8b3d

Aliases

arxiv: 2604.18995 · arxiv_version: 2604.18995v2 · doi: 10.48550/arxiv.2604.18995 · pith_short_12: TIX7TTQHAWJW · pith_short_16: TIX7TTQHAWJWHZHK · pith_short_8: TIX7TTQH

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/TIX7TTQHAWJWHZHK6TZD4W5YSF \
  | 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: 9a2ff9ce07059363e4eaf4f23e5bb891453b19464d9b8df1d190511e061e8b3d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2dad4755eb0bb5c4447a84b2a1015b9bbe5ebeb8cae3c921d23037e33eb9c64e",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-21T02:26:08Z",
    "title_canon_sha256": "9e621d39e21d23a456ac488e6555f72a06949cc38fad517d7292d6573e5b04ea"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.18995",
    "kind": "arxiv",
    "version": 2
  }
}