Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly ge...
Driving style captures stable, driver-specific patterns in how a vehicle is driven. In naturalistic data, however, this signal is hard to isolate because drivers are observed in di...
Since Volta introduced Independent Thread Scheduling (ITS), NVIDIA GPUs have been widely assumed to handle warp divergence in a fixed manner. We test this assumption across Ampere,...
Improving a language model today means retraining it: enormous compute, a new opaque model each cycle, non-deterministic output. We take the opposite path: the model stays frozen, ...
Parametric models of the human head are essential tools traditionally used in computer vision and graphics for animation, rendering, and reconstruction. More recently, they serve a...
Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high-quality images, videos, aud...
Bitcoin price prediction on sub-daily timescales is a hard open problem in computational finance. Bitcoin exhibits fat-tailed returns, non-stationary dynamics, and a price discover...
Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to com...
Large Language Models (LLMs) have transformed conversational AI, yet high-quality multilingual code-mixed dialogue resources remain scarce, particularly for Indic languages where s...
In this work, we aim to discretize the high-dimensional visual representations to bridge the gap with language models - a non-trivial challenge, as existing quantization methods su...
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering...
In visual storytelling, human performances are central to creative intent and narrative meaning. However, preserving human identity and performance while enabling flexible visual e...
In multilingual retrieval augmented generation, a retriever can retrieve relevant documents written in multiple languages, which are subsequently reranked before answer generation....
Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of the multimodal physical world....
Vision-language model (VLM) agents increasingly use tools to act on 3D scenes rather than only describe them. Existing 3D benchmarks score textual responses or single-object operat...
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task...
Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for hallucination detection, harnessing t...
Large Language Models (LLMs) have significantly automated the process of scientific discovery over the past few years. However, existing systems share one core limitation: they gen...
Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing restoration methods based on m...
Diffusion models typically suffer from error accumulation during iterative sampling, commonly referred to as exposure bias. We reveal systematic frequency-dependent discrepancies b...
Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two sources of dynamics: camera motion and object motion. This deco...
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While power...
On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teach...
Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry, into photorealistic videos...