Pith. sign in

REVIEW 11 cited by

MileBench: Benchmarking MLLMs in Long Context

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.18532 v2 pith:DPXU56C5 submitted 2024-04-29 cs.CL cs.AIcs.CVcs.LG

MileBench: Benchmarking MLLMs in Long Context

classification cs.CL cs.AIcs.CVcs.LG
keywords mllmslong-contexttasksbenchmarksmultimodalperformancebenchmarkcapabilities
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing benchmarks often focus on single-image and short-text samples, and when assessing multi-image tasks, they either limit the image count or focus on specific task (e.g time-series captioning), potentially obscuring the performance challenges of MLLMs. To address these limitations, we introduce MileBench, a pioneering benchmark designed to test the MultImodal Long-contExt capabilities of MLLMs. This benchmark comprises not only multimodal long contexts, but also multiple tasks requiring both comprehension and generation. We establish two distinct evaluation sets, diagnostic and realistic, to systematically assess MLLMs' long-context adaptation capacity and their ability to complete tasks in long-context scenarios. Our experimental results, obtained from testing 22 models, revealed that while the closed-source GPT-4o outperforms others, most open-source MLLMs struggle in long-context situations. Interestingly, the performance gap tends to widen with an increase in the number of images. We strongly encourage an intensification of research efforts towards enhancing MLLMs' long-context capabilities, especially in scenarios involving multiple images.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues

    cs.CV 2026-06 unverdicted novelty 7.0

    DiCoBench is a new high-resolution multi-image benchmark exposing large gaps between top MLLMs and human performance (98.3%) on differential and commonality visual cue perception.

  2. SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

    cs.CL 2026-05 unverdicted novelty 7.0

    SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heter...

  3. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.

  4. COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts

    cs.CV 2026-04 unverdicted novelty 7.0

    COHERENCE is a benchmark for MLLMs' fine-grained image-text alignment in interleaved multimodal contexts across four domains, with 6161 questions and six-type error analysis.

  5. COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts

    cs.CV 2026-04 unverdicted novelty 7.0

    COHERENCE is a new benchmark for measuring MLLMs' ability to recover fine-grained image-text correspondences in interleaved multimodal contexts.

  6. MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence

    cs.CV 2026-05 unverdicted novelty 6.0

    MMCL-Bench shows that even the strongest frontier multimodal models solve fewer than one-third of tasks requiring recovery and application of visual rules, procedures, and empirical patterns.

  7. Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration

    cs.CV 2026-05 unverdicted novelty 6.0

    A training-free attention-guided debiasing framework mitigates position bias in MLLM multi-image retrieval by exploiting the observed mismatch between biased logits and aligned attention maps, yielding over 40% accura...

  8. WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

    cs.CV 2026-05 unverdicted novelty 6.0

    WindowQuant performs window-adaptive mixed-precision KV cache quantization guided by similarity to the text prompt, with reordering to enable efficient inference in VLMs.

  9. RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction

    cs.LG 2026-04 unverdicted novelty 6.0

    RetentiveKV uses entropy to drive state-space model transitions that retain and reactivate low-attention visual tokens in a continuous memory instead of pruning them, delivering 5x KV cache compression and 1.5x faster...

  10. HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference

    cs.AI 2026-04 unverdicted novelty 6.0

    HybridKV reduces KV cache memory by up to 7.9x and speeds decoding by 1.52x in MLLMs with almost no performance loss by classifying heads into static and dynamic types and compressing them differently.

  11. CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

    cs.CV 2026-07 conditional novelty 5.0

    Multimodal context-learning benchmark CLBench-V separates grounding, information application, and knowledge acquisition; the best evaluated model scores 0.2847.