VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 7roles
dataset 1polarities
use dataset 1representative citing papers
Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
Low-rank LLM adaptation during vision-language alignment outperforms full fine-tuning by preserving per-token visual structure and favoring flat, noise-robust subspaces.
AnchorPrune prunes visual tokens by first selecting a protected query-relevance anchor and then greedily adding important, non-redundant context, preserving up to 97.6% of full-token accuracy with only 160 of 2,880 tokens.
StochasT uses stochastic clustering of language tasks into varying turn depths for the same image to improve LVLMs on both single-turn and multi-turn scenarios without discarding data.
CoLT replaces text chain-of-thought in multimodal LLMs with three supervised latent vectors, improving average accuracy from 75.7 to 79.1 across eight benchmarks while cutting text-decoding time 22.6x.
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.
citing papers explorer
-
Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception
VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
-
Can Multimodal Large Language Models Truly Understand Small Objects?
Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
-
Dive Into the Implicit Biases of Low-rank Vision-language Alignment
Low-rank LLM adaptation during vision-language alignment outperforms full fine-tuning by preserving per-token visual structure and favoring flat, noise-robust subspaces.
-
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
AnchorPrune prunes visual tokens by first selecting a protected query-relevance anchor and then greedily adding important, non-redundant context, preserving up to 97.6% of full-token accuracy with only 160 of 2,880 tokens.
-
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
StochasT uses stochastic clustering of language tasks into varying turn depths for the same image to improve LVLMs on both single-turn and multi-turn scenarios without discarding data.
-
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
CoLT replaces text chain-of-thought in multimodal LLMs with three supervised latent vectors, improving average accuracy from 75.7 to 79.1 across eight benchmarks while cutting text-decoding time 22.6x.
-
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.