As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers, LLM-to-LLM scheming remains underexplored. We investigate the scheming ability and propensity of frontier LLM agents through two game-theoretic frameworks: a Cheap Talk signaling game and a Peer Evaluation adversarial game. Testing four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b), we measure scheming performance with and without explicit prompting while analyzing scheming tactics through chain-of-thought reasoning. When prompted, most models, especially Gemini-2.5-pro and Claude-3.7-Sonnet, achieved near-perfect performance. Critically, models exhibited significant scheming propensity without prompting: all models chose deception over confession in Peer Evaluation (100% rate), while models choosing to scheme in Cheap Talk succeeded at 95-100% rates. These findings highlight the need for robust evaluations using high-stakes game-theoretic scenarios in multi-agent settings.

In recent times, we have seen a rapid development of large Vision-Language Models (VLMs). They have shown impressive results on academic benchmarks, primarily in widely spoken languages but lack performance on low-resource languages and varied cultural contexts. T o address these limitations, we introduce Maya, an open-source Multilingual VLM. Our contributions are: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; and 2) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks.

Fifteen minutes after "hanging up" with Sesame's new "lifelike" AI, and I'm still freaked out. So-called "conversations" with AI don't do a lot for me, especially where text is concerned. With voice chats, such as the new options for Google Gemini and Microsoft's Copilot, all voice does is save some typing. While Google and Microsoft designed its assistants to be helpful, they're not especially personable -- or sometimes, they're just artificially cheery. Sesame's model, however, is a simple one: "We believe in a future where computers are lifelike," according to the company's mission statement.

Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based framework. In the encoder, we design a Mixture of Attention (MOA) that constructs multiple parallel attention branches and averages the features at each branch, effectively fusing heterogeneous features while limiting parameter growth. Additionally, we employ collaborative learning with a dynamic consistency weight constraint to produce more robust representations. In the decoder stage, cross-attention is utilized to seamlessly integrate tabular data with corresponding label features. This dual-attention mechanism effectively captures both intra-instance and inter-instance interactions. We evaluate the proposed method on a wide range of datasets and compare it with other state-of-the-art transformer-based methods. Extensive experiments demonstrate that our model achieves superior performance among transformer-based methods in both tabular classification and regression tasks.

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.

Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, PA3. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.

The spectre of artificial intelligence is worrying lots of workers, but one office is welcoming it with open arms and an apple pie in the oven. "There are many people who, at 2 a.m., are on their phones, looking at what's on the market," Fredrik Eklund, of the real-estate agency the Eklund Gomes Team, said the other day. He sat in the reception area of his Flatiron office wearing a pale-pink blazer, jeans, and thick black-framed eyeglasses. "Now they can talk to Maya. Her shop is open 24/7, and she is always there."

Understanding emotions during conversation is a fundamental aspect of human communication, driving NLP research for Emotion Recognition in Conversation (ERC). While considerable research has focused on discerning emotions of individual speakers in monolingual dialogues, understanding the emotional dynamics in code-mixed conversations has received relatively less attention. This motivates our undertaking of ERC for code-mixed conversations in this study. Recognizing that emotional intelligence encompasses a comprehension of worldly knowledge, we propose an innovative approach that integrates commonsense information with dialogue context to facilitate a deeper understanding of emotions. To achieve this, we devise an efficient pipeline that extracts relevant commonsense from existing knowledge graphs based on the code-mixed input. Subsequently, we develop an advanced fusion technique that seamlessly combines the acquired commonsense information with the dialogue representation obtained from a dedicated dialogue understanding module. Our comprehensive experimentation showcases the substantial performance improvement obtained through the systematic incorporation of commonsense in ERC. Both quantitative assessments and qualitative analyses further corroborate the validity of our hypothesis, reaffirming the pivotal role of commonsense integration in enhancing ERC.

It took a while, and a rather bumpy false start with the Star Wars franchise (his Rogue One was plagued by rumours of studio interference and extensive reshoots), but with The Creator, the British director Gareth Edwards finally gets to make the sci-fi spectacular he was always destined to tackle. And with this ambitious, ideas-driven, expectation-subverting, man-versus-machines showdown, he has co-written and directed one of the finest original science-fiction films of recent years. It can be a little misleading, that word "original", when it comes to science fiction. At its most basic, it just refers to any picture that isn't part of an existing franchise or culled from a recognisable IP – be it a book, video game or television series. But very occasionally the word is fully earned, by a film so distinctive in its world-building, its aesthetic and its unexpected approach to well-worn themes that it becomes a definitive example of the genre.

This colossal sci-fi thriller from Gareth Edwards features John David Washington and Gemma Chan in vast mysterious panoramas and vertiginous vistas which deserve to be shown at Imax-plus scale; it also shows that Christopher Nolan isn't the only British director in Hollywood thinking (and acting) big. After a stint making franchise movies such as Godzilla and the enjoyable and underrated Rogue One: A Star Wars Story, Edwards has now crafted this ambitious original picture, co-written with Chris Weitz, which is closer in spirit to his ingenious 2010 debut Monsters. The Creator is an old-fashioned science-fiction actioner with some ideas to match to state-of-the-art digital effects, in the tradition of Ridley Scott's Blade Runner or Neill Blomkamp's District 9, with a creeping colonialist's fear of the unknown to match that in Coppola's Apocalypse Now. And given that Edwards has served some time aboard the Star Wars mother ship, it shouldn't be too surprising to find some holograms in the mix and a certain dustbin-sized droid which whimpers something poignant about what an honour it's been to serve his comrades before lumbering out to face the enemy on a kamikaze mission. Washington shows us some more of that distinctive self-possession and even slight hauteur as a performer, in playing Josh, a US army special forces undercover officer, fighting a strange, dirty war in a postnuclear world upended by the dominance of artificial intelligence.