Related papers: ExpAlign: Expectation-Guided Vision-Language Align…
Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels, we are dedicated to the…
Recent advancements in large language models (LLMs) focus on aligning to heterogeneous human expectations and values via multi-objective preference alignment. However, existing methods are dependent on the policy model parameters, which…
Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent…
Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…
Medical vision-language models (VLMs) show strong performance on radiology tasks but often produce fluent yet weakly grounded conclusions due to over-reliance on a dominant modality. We introduce a context-aligned reasoning framework that…
The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However,…
A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft…
Visual affordance learning is crucial for robots to understand and interact effectively with the physical world. Recent advances in this field attempt to leverage pre-trained knowledge of vision-language foundation models to learn…
Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However, existing methods usually follow an output-as-input latent…
Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment…
Effectively handling instructions with extremely long context remains a challenge for Large Language Models (LLMs), typically necessitating high-quality long data and substantial computational resources. This paper introduces Step-Skipping…
Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…
Visual Grounding (VG) aims to utilize given natural language queries to locate specific target objects within images. While current transformer-based approaches demonstrate strong localization performance in standard scene (i.e, scenarios…
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…
Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…
Open-vocabulary segmentation aims to achieve segmentation of arbitrary categories given unlimited text inputs as guidance. To achieve this, recent works have focused on developing various technical routes to exploit the potential of…
Mainstream approaches to aligning large language models (LLMs) heavily rely on human preference data, particularly when models require periodic updates. The standard process for iterative alignment of LLMs involves collecting new human…
Grounding natural language instructions to visual observations is fundamental for embodied agents operating in open-world environments. Recent advances in visual-language mapping have enabled generalizable semantic representations by…
Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to…
Reward Modeling is critical in evaluating and improving the generation of Large Language Models (LLMs). While numerous recent works have shown its feasibility in improving safety, helpfulness, reasoning, and instruction-following ability,…