InternVL3.5
PulseAugur coverage of InternVL3.5 — every cluster mentioning InternVL3.5 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New graph framework enhances emotion recognition in artworks
Researchers have developed Visual-Semantic Affect Graphs (VSAG), a novel graph-based framework for recognizing emotions in artworks. This approach models artworks by representing interpretable feature nodes, such as col…
-
Vision-Language Models Show Inverse Scaling on Specific Subtasks
A new research paper reveals that vision-language models (VLMs) can exhibit inverse scaling, meaning larger models sometimes perform worse than smaller ones on specific subtasks. This phenomenon was observed across 19 m…
-
New benchmark and module tackle object understanding after fire damage
Researchers have introduced TRACE, a new benchmark designed to evaluate object understanding capabilities in computer vision models after irreversible physical damage, such as that caused by fire. The benchmark includes…
-
New MMDiff framework enhances control and interpretability of multimodal LLMs
Researchers have developed MMDiff, a novel framework designed to enhance the interpretability and control of Multimodal Large Language Models (MLLMs). This system trains multimodal sparse autoencoders (SAEs) to identify…
-
MMDiff framework enhances multimodal LLM interpretability and control
Researchers have developed MMDiff, a new framework designed to enhance the interpretability and control of multimodal large language models (MLLMs). This system utilizes multimodal sparse autoencoders to isolate, detect…
-
New benchmarks and models advance vision-language capabilities in robotics and reasoning · 10 sources tracked
Recent research explores advancements in vision-language models (VLMs) across several domains. DeCAL introduces a new model for dexterous manipulation that integrates tactile sensing and visual-language understanding. R…
-
New method enhances MLLM privacy by drifting sensitive data
Researchers have developed Anchored Privacy Drifting (APD), a novel training-free method to enhance privacy in multimodal large language models (MLLMs). APD addresses challenges where user inputs and visual contexts may…
-
Zamba2-VL models offer faster vision-language processing
Researchers have introduced Zamba2-VL, a new family of vision-language models that leverage a hybrid architecture combining Mamba2 state-space layers with transformer blocks. These models demonstrate strong performance …