LLM Program Optimization via Retrieval Augmented Search
Recent work has demonstrated the potential of large language models (LLMs) for program optimization, a key challenge in programming languages. We propose a blackbox adaptation method…
Papers 5330 stories
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision…
SWE-Together: Evaluating Coding Agents in Interactive User Sessions
Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is…
RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets
RocketSmith is an agentic system which intelligently automates the DFAM process for the development of high powered rockets suitable for launch. The system utilizes a large…
A Gravitational Interpretation of Fine-Tuning Reversion
Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearned capabilities can re-emerge, latent traits can…
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Different real-time speech applications impose distinct latency budgets, often requiring separately trained enhancement models for each scenario. In this paper, we propose a one-for-all, real-time universal…
SAM2Matting: Generalized Image and Video Matting
Despite impressive advances in image matting, video matting remains challenging due to the inherent gap between high-level tracking, which requires frame-wise understanding, and low-level matting, which…
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
Modern large-scale LLM pretraining benefits from utilizing Pipeline Parallelism; however, synchronous implementations leave GPUs idle during pipeline bubbles, wasting computational resources. Asynchronous Pipeline Parallelism eliminates these…
One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth estimation,…
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or…
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks…
Beyond IID: How General Are Tabular Foundation Models, Really?
Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular…
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well…
ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains on the target distribution come at the cost of the foundation…
Large-Scale Tunnel Air-Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planner
Hydropower tunnel inspection is critical for infrastructure integrity yet remains inefficient and hazardous using manual methods. We propose FLISP (Fast LiDAR-IMU Synchronized Path Planner), a mapless…
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but…
TheoremGraph: Bridging Formal and Informal Mathematics
Mathematical knowledge is organized around statements and their dependencies, but this structure is exposed unevenly: informal papers cite mostly at the document level, while formal libraries…
Learning Transferable Dynamics Priors from Action to World Modeling
We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive…
The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector that fails under heavy occlusion,…
Interleaved Speech Language Models Latently Work In Text
Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading approach is speech-text interleaving in…
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events…
Trimming the Long-Tail of Visual World Modeling Evaluation
Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and…
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and…
DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model
We present DreamForge-World 0.1 Preview, a preview foundational world model for real-time interactive world simulation. The system adapts the LongLive 1 autoregressive video stack, itself derived…