Open Problems

Text-to-Image & Video Generation/Editing

Systematically Benchmarking and Calibrating VLM-as-a-Judge Failure Modes in Image and Video Generation

Barrier to removePartly addressed
Possible candidate · 2/5 runs15 papers report this100% from 2025+

Generated automatically from the limitations stated in 15 papers (CVPR, ICML, ICLR), listed under Evidence. It is not a paper, and it does not come from papers submitted to CSPaper.

The problem

Current text-to-image and video generation benchmarks overwhelmingly rely on Vision-Language Models (VLMs) like GPT-4o, Gemini, and Qwen-VL as automated judges for win rates and task success metrics. However, these VLM judges systematically exhibit low correlation with human raters on fine-grained visual details, suffer from position and same-family evaluator biases, and under-penalize visual artifacts such as boundary glitches or text corruption. Consequently, benchmark progress across generative models is structurally uninterpretable, as claimed state-of-the-art gains may reflect evaluator artifacts rather than genuine improvements in visual quality and prompt fidelity.

Why it matters

Enables reliable, reproducible benchmarking in generative text-to-image and video models without expensive full-scale human studies, ensuring reported win rates reflect true perceptual quality and semantic fidelity.

Ways to approach it

Prior-work checks are free with an account. Results someone already ran are shown to everyone.

  1. 1

    Multi-Judge Robustness and Bias Audit: Aggregate standard generated image/video evaluation datasets, run parallel evaluations across 6+ commercial and open-source VLM judges (e.g., GPT-4o, Claude 3.5, Gemini 2.5/3, Qwen2.5/3-VL), and measure rank stability, position bias, same-model bias, and Kendall tau / Spearman correlation against expert human visual error annotations.

  2. 2

    Fine-Grained Artifact Calibration Protocols: Build a diagnostic test suite isolating specific generation failure modes (e.g., text rendering, physical interaction, spatial relations, temporal boundary artifacts) and measure the sensitivity/recall of standard prompting protocols versus decomposed rubric-based multi-crop inspection prompting.

  3. 3

    Lightweight Task-Specific Rater Alignment: Evaluate whether small, open visual reward models fine-tuned on targeted human pairwise error distinctions can reliably de-bias frontier VLM judge scores across heterogeneous generator architectures.

Have a different approach?

Describe how you would tackle this problem and we'll look for papers that already do it. Free; your text stays private.

Free · 3 checks per day

Why it might fail

Frontier VLM providers may silently update model vision backbones to resolve fine-grained artifact blindness, or individual subfields may abandon automated VLM judging in favor of domain-specific reward models before a general audit is adopted.

Evidence

Each paper's own statement of the limitation, verbatim.

Show all 15 papers

Nearest existing work

Related open problems

Text-to-Image & Video Generation/Editing

Barrier to removePartly addressed

Benchmarking and Mitigating Upstream LLM Prompting Dependencies in Text-to-Visual Generation

Modern text-to-image and text-to-video generation and editing methods rely heavily on external large language models (LLMs) for prompt rewriting, sub-prompt decomposition, and attribute filtering. Consequently, visual generation quality is bottlenecked by upstream LLM biases, template artifacts, and hallucinated attributes, frequently failing on ambiguous or in-the-wild user instructions unless manually tuned. Because no systematic study has evaluated visual generation frameworks across diverse upstream prompt generators and decomposition strategies, the sensitivity and failure modes of these pipelines remain unquantified.

Possible candidate · 2/5 runs12 papers report this58% from 2025+

Text-to-Image & Video Generation/Editing

Barrier to removePartly addressed

Dense Motion Supervision Without Optical-Flow Ground Truth

Nearly every pipeline that needs dense correspondence—video generation control, camera pose estimation, motion attribution—currently anchors its supervision or its inference to optical flow, either ground-truth annotations or outputs of a pretrained model (RAFT, AllTracker). This couples training data to static-camera, high-quality, curated footage, caps dataset size (22k–630k pairs), injects flow errors directly into downstream quality (cycle-consistency errors >1000 px), and bakes in simplifying assumptions like first-frame conditioning or pinhole intrinsics. Every consumer of flow inherits the same ceiling set by flow estimators and the data they were trained on.

Strong candidate · 5/5 runs8 papers report this100% from 2025+
Generated automatically, not curated by hand. Automated prior-work checks catch about a third of existing work, so treat this problem as a lead to investigate.