Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distinguishing nearby positions. Determining which weaknes...
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
Post-training quantization (PTQ) has become a widely adopted technique for reducing the memory footprint and inference cost of large language models (LLMs). However, recent studies reveal that when ap...
Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned architectures must discover both a representation and...
Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene...
Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produces from what it discusses. We present Drift Insp...
Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketpla...
Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To this end, we present ECHO-G, a framework jointly...
A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out...
Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with existing methods reveal a collaps...
Trustworthy Legal AI requires systems that can answer legal questions while grounding their responses in authoritative sources. However, existing Vietnamese legal benchmarks provide limited coverage o...
Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is rewritten at every generated token. Storing this state in low precision saves memory bandwidth, but...
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human intention query and pr...
Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring in...
Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to...
Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate such healing code, but it is evaluated only on sm...
As new evidence arrives, a sequence model must update what it remembers and how memory influences predictions. While Transformers incur computation and cache costs scaling with context length, fixed-s...
Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, often rely on coarse-g...
A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let code turn the count into a label. The latter is easie...