논문해외HF Daily Papers
ReproBridge: Building Reproducibility into ML Research Artifacts
Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts.
실시간
국내외 뉴스 · 기업 공식 발표 · 논문 · 영상 · 커뮤니티 소식을 한국시간 기준으로 제공합니다. 같은 소식은 하나로 묶고, 기본은 핵심만 보여 드립니다.
모든 수집 소식(구글 뉴스로 들어온 단건 보도 포함).
Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts.
Linear attention compresses context into a fixed-size key-value state for linear-time training and constant-memory inference.
LLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory.
We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that…
Reinforcement learning (RL) has become a standard post-training method for diffusion models, but most RL objectives roll out the current policy at every…
Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only…
On-Policy Self-Distillation (OPSD) improves reasoning by training a student on its own reasoning, using the same model conditioned on reference solutions as a…
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules.
Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled.
Protein motif scaffolding benchmarks assess whether generative models can build scaffolds around functionally important residues.
LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and…
Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual…
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they…
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods…
We present WeLM-Image, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and…
Current medical benchmarks typically break down clinical competence into isolated factual questions, single-image tasks, or static case vignettes.
Reliable robotic manipulation requires both semantic understanding and precise control in three-dimensional space.
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language.
When firms respond to new market opportunities, their capacity choices alter the future discounted free cash flows available to both competitors and investors.
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining…
Agent harness evolution enables recursive self-improvement (RSI) without updating model weights.
How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal-Bench…
Intra-weight injection lets one model change another model's behaviour by editing its weights directly, without gradients.
Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest.
Different optimizers impose different geometries on parameter updates. Adaptive methods such as Adam and AdamW use coordinate-wise updates, while matrix-aware…
Visual interaction models that support users during ongoing physical tasks require evaluation in closed loop, where assistant responses can change subsequent…
Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity…
Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks.
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput.
Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only…