Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose ECI_{sem}, a semantic residual variant of Effecti...
Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and...
Multiple Instance Learning (MIL) addresses problems where supervision is available at the level of bags of instances and has been successfully applied in fields ranging from comput...
Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks via domain-expert LL...
AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing ...
Retrieval-augmented QA pipelines often route retrieved passages through an LLM rewriter before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is ...
Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been...
Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier field. Existing unified framewo...
We propose world-language-action (WLA) models as a new class of embodied foundation models. WLA takes textual instructions, images, and robot states as inputs to jointly predict te...
Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, ...
Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces t...
Video event prediction (VEP) requires models to infer unobserved future states from partial video evidence. Existing video MLLMs usually verbalize intermediate future reasoning in ...
Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution...
Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However, ...
On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from ...
Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these lat...
Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs. We study post-hoc compression of such traces before knowledg...
We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substi...
Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed through...
Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatia...
Vision-Language-Action (VLA) models leverage the rich world knowledge of pretrained vision-language models (VLMs) to enable instruction-following robotic manipulation. However, the...
Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG o...
A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting...
Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their construction is labor-intensiv...