Knowledge catalogue
Sophia Yang posted that she was attending Day 2 of the AIconference with the FireworksAI_HQ team. She highlighted discussions on model inference and training among other AI topics. The tweet received
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff bet
arXiv:2609.38811v1 Announce Type: new Abstract: Metal additive manufacturing parts are inspected by X-ray computed tomography, where labelled data is scarce, the pores and inclusions that matter span
Hello everyone. I've recently ran some experiments comparing DDR4/PCIe4 and DDR5/PCIe5 for AI workstations on a pre-training run, and would like to hear yours thoughts. First of all, and as a summary
arXiv:2508.12145v5 Announce Type: replace Abstract: Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projection
arXiv:2609.40124v1 Announce Type: new Abstract: Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that re
arXiv:2501.18183v3 Announce Type: replace-cross Abstract: We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-l
arXiv:2609.40241v1 Announce Type: cross Abstract: Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation qu
arXiv:2609.38386v1 Announce Type: new Abstract: Concurrent autoregressive inference creates a fundamental interference problem: prefilling a newly arrived long prompt can delay tokens for requests tha
arXiv:2609.38823v1 Announce Type: new Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becaus
arXiv:2609.39096v1 Announce Type: new Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compre
arXiv:2609.39390v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previ
arXiv:2505.05855v4 Announce Type: replace Abstract: Multi-contrast super-resolution (MCSR) is crucial for enhancing MRI but current deep learning methods are limited. They typically require large, pai
arXiv:2609.38856v1 Announce Type: new Abstract: The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent featu
arXiv:2609.38510v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive LLMs by having a lightweight drafter propose tokens that the target model verifies in parallel. Diffusio
Optional Bundle architecture: Schedule (session-local delayed / timed / interval reminders) was removed from the default set and made an explicit Optional Bundle. This cleanly separates “installed” fr
arXiv:2609.38559v1 Announce Type: new Abstract: This paper examines human-AI interactions (HAIIs) in clinical trials and presents a multidimensional categorisation framework that classifies interactio
arXiv:2603.10210v2 Announce Type: replace-cross Abstract: While Diffusion Models excel in text-to-image synthesis, they frequently suffer from catastrophic concept omission when generating complex mul
This is the first of a two-part series exploring how Google Cloud is bringing the foundational values of a high-performance parallel filesystem–TB/s throughput, sub-ms latency at high client scale, an
arXiv:2609.38555v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in culturally sensitive settings, where alignment requires representing diverse preferences within po
arXiv:2609.38617v1 Announce Type: new Abstract: Legged robots can learn expressive whole-body skills from the motions of humans and animals. Due to the morphology gap between the source and the robot,
arXiv:2609.39467v1 Announce Type: new Abstract: Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-wor
arXiv:2512.22819v2 Announce Type: replace Abstract: Panoramic depth estimation captures the complete 360^irc scene geometry, being essential for robotics and AR/VR applications. While perspective dept
arXiv:2609.38471v1 Announce Type: cross Abstract: Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level si
arXiv:2609.38560v1 Announce Type: new Abstract: Mycosis fungoides (MF) is a rare form of cutaneous T-cell lymphoma that is often misdiagnosed in early stages due to its visual similarity to benign inf
arXiv:2609.39756v1 Announce Type: new Abstract: This article introduces an algorithm that uses a U-Net architecture to determine vertical ground surface displacements from unmanned aerial vehicle (UAV
arXiv:2609.39118v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models. Without e
arXiv:2401.13937v3 Announce Type: replace Abstract: Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object r
arXiv:2609.39098v1 Announce Type: cross Abstract: Perceiving human motion via privacy-preserving 4D millimeter-wave (mmWave) radar is critical for next-generation human-robot interaction (HRI), where
arXiv:2509.02109v3 Announce Type: replace Abstract: The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gau
arXiv:2609.38618v1 Announce Type: cross Abstract: We study causal structure learning from observational data in linear Gaussian structural causal models in the presence of directed cycles and an unkno
arXiv:2609.39657v1 Announce Type: new Abstract: Distilling pretrained foundation models into an autoencoder bottleneck improves latent diffusability, enabling diffusion models to converge faster and r
arXiv:2609.38472v1 Announce Type: cross Abstract: Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstration
arXiv:2609.39763v1 Announce Type: cross Abstract: Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion
An AI agent uses compute differently than a traditional application. Over a single session, it writes and runs code, calls a model, and waits on a tool or a person before picking the work back up. As
arXiv:2609.39855v1 Announce Type: new Abstract: We study the width required for a randomly initialized hidden layer of a neural network to achieve rank lifting. Namely, given a dataset X in R^{m imes
arXiv:2609.38407v1 Announce Type: new Abstract: Purpose: Behavior cloning can accumulate errors when a learned controller visits states outside the demonstrated distribution. This study evaluates whet
arXiv:2609.39526v1 Announce Type: new Abstract: Efficient action generation in vision-language-action (VLA) models requires capturing both coarse action structure and fine-grained details. Discrete ac
arXiv:2609.39326v1 Announce Type: cross Abstract: Count data pose a challenge for score-matching-based causal discovery: derivatives are unavailable, and simply replacing them with finite differences
arXiv:2609.40292v1 Announce Type: new Abstract: How is computation organized and reused across tasks and time in a trained recurrent network? Most analyses emphasize the geometry of neural activity, d
arXiv:2609.39494v1 Announce Type: new Abstract: Self-distillation with privileged context adapts a language model from demonstrations by letting the model, once conditioned on a reference response, te
arXiv:2609.38777v1 Announce Type: new Abstract: A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. However
arXiv:2609.38776v1 Announce Type: cross Abstract: Training data attribution for diffusion models aims to identify the training samples that influence a generated instance, but existing methods either
arXiv:2609.40235v1 Announce Type: cross Abstract: Continuous diffusion language models generate all tokens in parallel, yet high-quality generation can still require hundreds of network evaluations (N
arXiv:2609.39449v1 Announce Type: cross Abstract: Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged a
arXiv:2609.38829v1 Announce Type: new Abstract: Multi-path reasoning methods such as self-consistency (SC) sample K reasoning paths and choose the most frequent answer. However, their gains quickly pl
arXiv:2609.39559v1 Announce Type: new Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produc
Evolving MLPerf Training from feature-interaction baselines to production-scale sequential recommendation with HSTU and the 560 GB Yambda-5B embedding benchmark. The post DLRMv4: The Next-Generation R
arXiv:2609.39901v1 Announce Type: cross Abstract: Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via
arXiv:2609.39148v1 Announce Type: new Abstract: AI agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, tha
arXiv:2609.38374v1 Announce Type: new Abstract: Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innov
arXiv:2609.38873v1 Announce Type: new Abstract: Robots operating in human-centered environments must safely navigate among multiple dynamic obstacles to avoid collisions with people and surrounding in
arXiv:2609.38784v1 Announce Type: new Abstract: In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold
arXiv:2609.38465v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) are increasingly designed around gradient conflict between understanding and generation objectives. The premise that
arXiv:2609.38879v1 Announce Type: cross Abstract: Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protei
arXiv:2609.38517v1 Announce Type: new Abstract: Lower error from a text-conditioned neural surrogate does not, by itself, show that the model uses the meaning of the text. We examine this attribution
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, b
arXiv:2609.39909v1 Announce Type: cross Abstract: We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing soft
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gene
arXiv:2609.31688v2 Announce Type: replace Abstract: In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt.