Latest AI/ML research from ArXiv and Papers with Code
LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, a...
Coding agents combine visual understanding with program execution, offering a new route to automated 3D creation. By translating images and instructions into editable programs, the...
3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result se...
Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, ...
Weight-Space Programming (WSP) enables reasoning agents to directly inspect and modify neural network parameters, offering an alternative to gradient-based model adaptation. Howeve...
Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We sho...
Language model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single...
Linear attention compresses context into a fixed-size key-value state for linear-time training and constant-memory inference. Gated delta-rule models decay this state and erase its...
LLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory. Existing pruning workflows often target parameter co...
We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global ra...
Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both clos...
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 teacher. Applying OPS...
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents c...
Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled. Existing analyses count how often an ...
Protein motif scaffolding benchmarks assess whether generative models can build scaffolds around functionally important residues. Their conclusions depend on which motifs are teste...
LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces...
Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual token-level information, suc...
We present WeLM-Image, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synt...
Current medical benchmarks typically break down clinical competence into isolated factual questions, single-image tasks, or static case vignettes. These tests score individual answ...
When firms respond to new market opportunities, their capacity choices alter the future discounted free cash flows available to both competitors and investors. In competitive marke...
Reliable robotic manipulation requires both semantic understanding and precise control in three-dimensional space. However, vision-language-action (VLA) foundations largely inherit...
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to r...
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on...
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. ...