Found 4,326 document(s)
Page 16 of 289
-
Diffusion models primarily rely on general-purpose ODE-based numerical methods for training-free accelerated sampling, but performance degrades with coarse time discretization. In this paper, we propose optimal linear le...
-
As language models are increasingly deployed in real-world scenarios with important outcomes, the impact of their mistakes often extends far beyond what correctness can capture. In domains like medicine, a single error c...
-
Deep research agents are increasingly capable of searching the open web and synthesizing evidence, yet they remain poorly suited to controllable report generation in multimodal deep research. This task requires agents to...
-
Omni-modal large language models can jointly understand video, audio, and text, yet they remain weak at temporal grounding, a capability essential for real-world audio-visual applications. To understand this limitation, ...
-
Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics. However, existing benchmarks ra...
-
Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasoning? We introduce \method, a framework that jointly ...
-
Chain-of-thought (CoT) reasoning can improve problem solving, but models often keep generating after the correct answer is already reachable; the extra steps raise serving costs and may replace a correct intermediate res...
-
Long-horizon search requires agents to acquire relevant evidence and integrate it into an evolving research state. Existing methods maintain research states to guide exploration or assign turn-level progress signals, yet...
-
Multimodal Mixture-of-Experts (MoE) reasoning models rely on long chain-of-thought (CoT) for complex tasks, yet often overthink easy inputs, increasing token cost and latency, and sometimes degrading accuracy. Existing m...
-
Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousan...
-
Performing accurate protein-glycan docking is critical to understanding protein-glycan interactions which govern many biological processes. However, this important task is hampered by the lack of tailored datasets, bench...
-
LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the guardrail model becomes smaller or weaker, detection degrades substantially. T...
-
While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in the aerial domain, where extreme scale variations and visual ambiguity ab...
-
Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has improved video reasoning in multimodal large language models. However, standard video GRPO varies only linguisti...
-
Referring segmentation in low-altitude drone imagery requires distinguishing small, visually similar instances under complex linguistic and spatial constraints. Global inference may yield multiple plausible masks or leav...