Related papers: TRACE: Textual Relevance Augmentation and Contextu…
Existing self-supervised learning strategies are constrained to either a limited set of objectives or generic downstream tasks that predominantly target uni-modal applications. This has isolated progress for imperative multi-modal…
Memes are popular in the modern world and are distributed primarily for entertainment. However, harmful ideologies such as misogyny can be propagated through innocent-looking memes. The detection and understanding of why a meme is…
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…
Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead,…
Stance detection on social media is challenging for Large Language Models (LLMs), as emerging slang and colloquial language in online conversations often contain deeply implicit stance labels. Chain-of-Thought (COT) prompting has recently…
The automated detection of sexism in memes is a challenging task due to multimodal ambiguity, cultural nuance, and the use of humor to provide plausible deniability. Content-only models often fail to capture the complexity of human…
The rapid rise of video content on platforms such as TikTok and YouTube has transformed information dissemination, but it has also facilitated the spread of harmful content, particularly hate videos. Despite significant efforts to combat…
Hateful videos present serious risks to online safety and real-world well-being, necessitating effective detection methods. Although multimodal classification approaches integrating information from several modalities outperform unimodal…
The phenomenal growth on the internet has helped in empowering individual's expressions, but the misuse of freedom of expression has also led to the increase of various cyber crimes and anti-social activities. Hate speech is one such issue…
This work investigates the challenging task of identifying narrative roles - Hero, Villain, Victim, and Other - in Internet memes, across three diverse test sets spanning English and code-mixed (English-Hindi) languages. Building on an…
Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…
Hate speech in social media is a growing phenomenon, and detecting such toxic content has recently gained significant traction in the research community. Existing studies have explored fine-tuning language models (LMs) to perform hate…
In the digital era, effective identification and analysis of verbal attacks are essential for maintaining online civility and ensuring social security. However, existing research is limited by insufficient modeling of conversational…
Memes have emerged as a powerful form of communication, integrating visual and textual elements to convey humor, satire, and cultural messages. Existing research has focused primarily on aspects such as emotion classification, meme…
Stance detection plays a pivotal role in enabling an extensive range of downstream applications, from discourse parsing to tracing the spread of fake news and the denial of scientific facts. While most stance classification models rely on…
Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…
The presence of sarcasm in conversational systems and social media like chatbots, Facebook, Twitter, etc. poses several challenges for downstream NLP tasks. This is attributed to the fact that the intended meaning of a sarcastic text is…
The detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining…
With the rapid advancement of generative AI, synthetic content across images, videos, and audio has become increasingly realistic, amplifying the risk of misinformation. Existing detection approaches predominantly focus on binary…
Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…