Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions

Pengcheng Lyu, Chaokun Zhang, Gong Chen, Tao Tang +1 more

Published

Apr 2, 2026

Citations

0

Trust level

Moderate

Usefulness score

35/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Apr 2, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics General Multi Agent

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this for comparison and orientation, not as your only source.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the exact study setup in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
35/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence. However, real-world sensor and communication corruptions severely undermine this advantage. Crucially, existing approaches treat corruptions as static perturbations or passively conform to corrupted inputs, failing to actively recover the underlying clean semantics. To address this limitation, we introduce Diff-KD, a framework that integrates diffusion-based generative refinement into teacher-student knowledge distillation for robust collaborative perception. Diff-KD features two core components: (i) Progressive Knowledge Distillation (PKD), which treats local feature restoration as a conditional diffusion process to recover global semantics from corrupted observations; and (ii) Adaptive Gated Fusion (AGF), which dynamically weights neighbors based on ego reliability during fusion. Evaluated on OPV2V and DAIR-V2X under seven corruption types, Diff-KD achieves state-of-the-art performance in both detection accuracy and calibration robustness.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence."

Quality Controls

strong

Calibration

Calibration/adjudication style controls detected.

"Evaluated on OPV2V and DAIR-V2X under seven corruption types, Diff-KD achieves state-of-the-art performance in both detection accuracy and calibration robustness."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence."

Reported Metrics

strong

Accuracy

Useful for evaluation criteria comparison.

"Evaluated on OPV2V and DAIR-V2X under seven corruption types, Diff-KD achieves state-of-the-art performance in both detection accuracy and calibration robustness."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Multi Agent
Quality controls
Calibration
Evidence quality
Moderate
Use this page as
Background context only

Research brief

Metadata summary

Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.
  • However, real-world sensor and communication corruptions severely undermine this advantage.
  • Crucially, existing approaches treat corruptions as static perturbations or passively conform to corrupted inputs, failing to actively recover the underlying clean semantics.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Accuracy

Contribution summary

  • Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.
  • To address this limitation, we introduce Diff-KD, a framework that integrates diffusion-based generative refinement into teacher-student knowledge distillation for robust collaborative perception.
  • Evaluated on OPV2V and DAIR-V2X under seven corruption types, Diff-KD achieves state-of-the-art performance in both detection accuracy and calibration robustness.

Why it matters for eval

  • Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    Detected: Calibration

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy