While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy duri...
On-policy distillation (OPD) trains a student on prefixes sampled from its own policy while matching a stronger teacher. This addresses the prefix mismatch of offline distillation,...
Effective real-world assistance requires AI agents with robust Theory of Mind (ToM): inferring human mental states from their behavior. Despite recent advances, several key challen...
True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under different conditions, and d...
Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-...
Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important. A minimal intervention is ...
LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing ski...
Most text-driven 3D indoor scene synthesis methods generate rooms from object-centric prompts, asking what furniture should be placed rather than how the space is used. Yet in real...
Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that...
Speech translation systems increasingly span speech-to-text translation (S2TT), speech-to-speech translation (S2ST), offline translation, and streaming generation, producing output...
Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or...
Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference data from human annotation ...
Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing counting models are often tai...
Learning mappings between infinite-dimensional function spaces, or operator learning, is essential for many machine learning applications. Although transformer-based operators are ...
Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and beyond the training horizon the...
We examine whether human psychometric questionnaires can serve as reliable tools for characterizing and predicting LLM behavior in everyday user interactions. We analyze eight open...
Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed sin...
While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introd...
Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm s...
Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical eng...
Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-level supervision. Semantic corr...
Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic op...
We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential ...
Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API v...