MLINFO COLLECTION
Managed and wild bees sustain roughly a third of the global food products, yet colonies face mounting stress from climate-change including extreme weather patterns, altered parasite and disease…
Masked diffusion language models have emerged as an alternative to autoregressive models, enabling parallel token generation. However, standard masked diffusion language models use a shared noise…
People share and understand others' experiences differently based on their social identities; often, people empathize more when the other person belongs to their ingroup compared to an outgroup.…
Agentic search depends on the interface through which a language-model agent accesses and explores a corpus. Existing interface designs are fixed by hand and applied unchanged to every corpus,…
Predictive representations for robot manipulation should connect scene geometry with the state changes induced by actions. Our intuition is that understanding what an action will change starts with…
Vision-Language Models (VLMs) excel at 2D recognition but often fail to maintain consistent 3D relations across sparse viewpoints, leading to spatial hallucinations under occlusion and perspective…
Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and suffering from low consistency across automated judges. To address this, we introduce…
Retrieval-augmented generation can expose unwanted concepts through retrieved evidence even when the generator is moderated. We study query-side concept suppression with a fixed encoder and document…
Decision models return normalized probability distributions over candidate choices, which downstream applications can use to select among choices. Although their providers emphasize the reliability…
Personalized shopping benchmarks ask which item fits the user; we ask how far an agent may commit on that item, and pose learning the individual's auto-purchase line as a task. The boundary is…
Human-in-the-loop (HIL) post-training improves vision-language-action (VLA) policies through expert corrections, but costly human supervision and repeated real-robot evaluation limit algorithm…
Reward guidance methods sample an exponential tilt of a base density using a diffusion model trained with only samples from the base distribution. Existing methods use what we call external guidance:…
Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStream 1.0 introduced the first…
Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on…
Autonomous agents can increasingly propose ideas, modify code, and run experiments, creating an opportunity to accelerate scientific discovery using teams of collaborative AI researchers. To escape…
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through…
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage…
Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across controlled variations…
People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by the user.
Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on…
Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to score the candidates of a query. Scoring options is not specific to reranking.
Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs)…
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end…
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by…