AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing their LLMs to unvetted third-party content. Browsers enforce semantics under which what an element can do depends on what it…
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the quality of individual ideas, while overlooking diversity. In o…
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associated with notes, whereas beats may occur without coincident n…
Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce ReviewFact, a benchmark that labels such factual errors in review comments under one defin…
Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), video references (e.g., camera movement), or a combination of the above. We introduce Omn…
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precompute…
Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different messages, know d…
When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra thinking does to such everyday inference…
Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchmark exists to compare, study and improve these models. Through this p…
Augmenting softmax attention with forget gates typically relies on summing decay contributions along the key--query path. Because such accumulation is monotonic, these mechanisms cannot selectively erase intermediate context while preservi…
Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such settings impose industrial process constraints…
Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for reducing compliance with targeted undesirable instructions.…
Harness evolution automatically optimizes the prompts, skills, tools, and orchestration code around a fixed-weight model, offering a way to improve agentic systems without updating model weights. The agent harness is iteratively optimized…
Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verified, goal-specified research tasks spanning strong-field, a…
Large language models (LLMs) are increasingly used in critical domains, where their susceptibility to hallucinations makes reliable and interpretable uncertainty quantification essential. We introduce the concept of mechanistic uncertainty…
Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research also requires scientific judgment. Evaluating scientific judgment is difficult because res…
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a controlled comparison of data-level and training-level interven…
ARTIFICIAL INTELLIGENCE (AI) has demonstrated its potential across a wide range of humanitarian tasks, offering scalable and data-driven solutions to some of the world's most pressing challenges. For instance, in addressing climate change,…