Unverified50% confidenceBenchmarkExact time
Three VLMs all improved in exact-match rate on four scientific chart benchmarks, with a single maximum improvement of 55.2 percentage points.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Q3_K_M quantized model's accuracy improved from 52% to 66%, representing the largest improvement.76% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.71% similarUnverifiedPiPMRE achieves an average improvement of 4.4 percentage points in precision over the previous state-of-the-art methods on two public datasets.67% similarUnverifiedOn the Qwen3-VL-4B model, fine-tuning with procedurally generated data raises its accuracy on SpaceCast-Bench from 34.0% to 65.7%, and achieves a macro-average gain across six out-of-domain benchmarks.67% similarUnverifiedUnder the synthetic settings evaluated, DASA provides a 3.6 to 4.9× speedup compared to GRADMM, with comparable peak GPU memory usage.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102162API
curl https://kongchang.com/api/v1/knowledge/claims/1102162MCP
get_claim(id=1102162)