V$^*Bench
PulseAugur coverage of V$^*Bench — every cluster mentioning V$^*Bench across labs, papers, and developer communities, ranked by signal.
-
New research explores "two clocks" in diffusion LMMs: answer stabilization vs. rationale unfolding
A new research paper introduces the concept of "two clocks" in diffusion Large Multimodal Models (LMMs), distinguishing between when an answer stabilizes and when its rationale is fully generated. The study analyzes thi…
-
New GAM-Agent framework boosts visual reasoning in LLMs via game theory
Researchers have developed GAM-Agent, a novel framework that enhances visual reasoning in large language models by employing a game-theoretic approach. This system treats the reasoning process as a non-zero-sum game whe…
-
New benchmarks and methods advance multimodal reasoning in AI
Researchers are developing new methods for multimodal knowledge graph completion and reasoning, integrating vision-language models (VLMs) with graph structures. ViSR-KGC proposes a visual subgraph reasoning approach tha…
-
New 'Thinking-Once' method improves high-resolution VQA by routing existing evidence
Researchers have developed a new method called Thinking-Once for high-resolution visual question answering (HR-VQA). This technique focuses on efficiently routing evidence that is already present in intermediate layers …
-
New HART technique enables LMMs to reason with high-resolution images without annotations
Researchers have developed a new technique called HART (High-resolution Annotation-free Reasoning Technique) to improve how Large Multimodal Models (LMMs) handle high-resolution images. Current LMMs struggle with the la…
-
New methods accelerate agentic LLM inference with speculative execution · 2 sources tracked
Two research papers introduce novel methods to accelerate the inference speed of agentic large language models (LLMs) by employing speculative execution. The first paper, SPORK, utilizes a lightweight probe from the LLM…
-
ActiveScope framework enhances MLLM perception by correcting errors
Researchers have introduced ActiveScope, a novel training-free framework designed to improve the perception capabilities of Multimodal Large Language Models (MLLMs). This framework addresses limitations in high-resoluti…
-
HiDe framework boosts MLLM performance on high-res images
Researchers have developed a new training-free framework called HiDe to improve the performance of Multimodal Large Language Models (MLLMs) on high-resolution images. HiDe addresses background interference rather than o…
-
Perceptual Flow Network and VGR enhance visual reasoning in LLMs
Researchers have developed a Perceptual Flow Network (PFlowNet) to improve visual reasoning in Large-Vision Language Models (LVLMs). PFlowNet decouples perception from reasoning and uses variational reinforcement learni…
-
SIEVES method boosts multimodal LLM coverage on visual tasks with evidence scoring
Researchers have developed SIEVES, a novel method for improving the reliability of multimodal large language models (MLLMs) in out-of-distribution scenarios. SIEVES works by learning to estimate the quality of visual ev…