相关论文: Silkie: Preference Distillation for Large Visual L…

Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in…

Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human annotations. Existing methods relying on direct distillation…

Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement learning with verifiable rewards provides on-policy exploration…

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM (l-MLLM). Our approach tackles two fundamental challenges…

Machine Translation (MT) is undergoing a paradigm shift, with systems based on fine-tuned large language models (LLM) becoming increasingly competitive with traditional encoder-decoder models trained specifically for translation tasks.…

Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with…

We aim to produce a smaller language model that is aligned to user intent. Previous research has shown that applying distilled supervised fine-tuning (dSFT) on larger models significantly improves task accuracy; however, these models are…

Medical Large Vision-Language Models (Med-LVLMs) have shown promising results in clinical applications, but often suffer from hallucinated outputs due to misaligned visual understanding. In this work, we identify two fundamental limitations…

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization…

Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confidently assert a five-legged dog has four legs; consequently, on the VLMBias benchmark, GPT 5.2…

Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on…

Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using…

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces…

Large vision-language models (LVLMs) remain vulnerable to hallucination, often generating content misaligned with visual inputs. Although recent training-based approaches aim to mitigate hallucination, they typically rely on predefined or…

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the…

Stated preference (SP) surveys are a key method to research how individuals make trade-offs in hypothetical, also futuristic, scenarios. In energy context this includes key decarbonisation enablement contexts, such as low-carbon…

The development of large vision-language models (LVLMs) offers the potential to address challenges faced by traditional multimodal recommendations thanks to their proficient understanding of static images and textual dynamics. However, the…