MLINFO COLLECTION
An AI system can produce more economically valuable work while delivering less value for the energy it consumes. We therefore ask: How much economic value does an AI system create per unit of energy…
Trained network weights are increasingly treated as data, but there is rarely ground truth about what a population of models should encode, which hampers systematic validation of weight-space…
We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial training and input-level query rewriting. Human…
Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered. Yet current multimodal benchmarks…
Long chain-of-thought reasoning improves vision-language models (VLMs), but it also exposes a temporal grounding failure: as generation unfolds, models may drift from image evidence while…
LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a…
The increasing adoption of generative AI presents new opportunities while raising AI governance and regulatory challenges, particularly for small and medium-sized enterprises (SMEs) navigating the…
Loco-manipulation extends the workspace of conventional manipulation by combining mobility with physical interaction, while aerial loco-manipulation further expands this capability into…
KV caching reduces the serving cost of large language models (LLMs), but the growing KV cache footprint is increasingly exceeds GPU and host-memory capacity. Therefore, people use SSD to expand the…
Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses. Therefore, they increasingly refuse or hedge when such attributes appear…
Graph anomaly detection (GAD) aims to identify irregular entities in graph-structured data, yet heterogeneous anomaly patterns and distributional differences across graphs challenge generalizable…
Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social…
We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thinking judges trained with…
AI assistants built on large language models (LLMs) are trained on human feedback and increasingly personalized to users' stated preferences. Yet how closely these preferences reflect what people…
AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's identity. We investigated whether experienced underwriters and loan processors…
Representation learning has substantially improved the efficiency of unconstrained continuous-state Markov Decision Processes (MDPs), but its extension to Constrained MDPs (CMDPs) is difficult…
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations.
Guardrail models are increasingly used as safety layers for LLMs and agentic systems, but most are trained on fixed prompt or response interfaces and become unreliable when the same safety case…
Shadows are observable consequences of latent physical causes, arising from the interaction between illumination, object geometry, and scene structure. A model that understands shadows should be able…
When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence through…
Large language models have been reported to encode the harmfulness of a request separately from their decision to refuse it, and latent safety monitors such as Latent Guard build on this report by…
Recent advances in text-to-video generation have substantially improved visual fidelity, yet existing models still struggle to understand the physical evolution implicit in user prompts, making it…
This paper studies the local geometry of semantic meaning in large language models. Current representation analyses ask whether meanings are close in embedding space, or whether linear probes…
Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a…