Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks often emphasize successful, cooperative interactions and underrepresent adversarial conversa...
Arkajyoti Chakraborty, Aryan Tayal, Ishika Agarwal et al.· 0 citations
Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-bench, a native-first Slovak benchmark with 30 datasets (33 scored task variants) across ten skill categories. Eleven resources are introduced or first pa...
Marek Suppa, Ivan Vykopal, Andrej Ridzik et al.· 0 citations
Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid, low-rate, and benign-looking while the population collectively acquires broad system knowledge. We formalize this threat as Distributed Collective Reconnaissance (DCR) and present SwarmReconGuard, a r...
Vahid Tavakkoli, Kabeh Mohsenzadegan, Kyandoghere Kyamakya· 0 citations
Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant to a prediction forms a contiguous block. In multidimensional data, serialization breaks this assumption by scattering spatial neighbors across distant positions in the...
Kimia Kazemian, Menghan Xu, John Thickstun et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (maximizing expected return) is notoriously non-convex, even under a direct policy parameterization, and the field has largely responded by avoiding it:...
Shripad Deshmukh, Yaswanth Chittepu, Dhawal Gupta et al.· 0 citations
State Space Models (SSMs) offer an efficient alternative to Transformers for sequence modeling, yet conditioning pre-trained SSMs for iterative generation typically operates outside the recurrent operator, through input injection or activation modulation. While such mechanisms expose the model to conditioning informati...
Syed Ibrahim Omer, Ginny Y. Wong. Xiangyu Zhao· 0 citations
Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer? Yet recognizing when to defer remains difficult because language models can present incorrect conclusions with fluent...
Tobias Braun, Nils Loose, Alexander Herzog et al.· 0 citations
When we interact with large language models (LLMs), are we having a conversation? They are designed to invite us to treat them as intelligent interlocutors who remember, act, and make commitments. But appearances deceive. We introduce the artifactual stance, a framework that reconceives human-AI interaction as artifact...
James Ravi Kirkpatrick, Alexandru Radulescu, Rachel Katharine Sterken· 0 citations
Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We present MimicX, a policy-in-the-loop framework that uses execution feedback to refine...
Shuaijun Liu, Chenglong Zhang, Xuhao Liu et al.· 0 citations
In human-AI collaborative decision making, human review can prevent unsafe AI decisions, but each human judgment is costly. Treating human intervention after AI abstention as a one-off fallback misses the opportunity to improve future AI decisions for greater automation, yet AI adaptively learning from selectively quer...
Chenyu Zhang, Rachel Luo, Boyi Li et al.· 0 citations
Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment routinely receive inputs containing emojis, altered spellings, encoded strings, and character-level variations. This work introduces the Adversarial Surface-Form Robustness...
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even after that input is removed from its context? We show that attacks can be trained to persist through the key/value (KV) cache of subsequent tok...
David Dobre, Leo Schwinn, Gauthier Gidel et al.· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
