A linearized solver estimates rolling-shutter relative pose and motion from 7 affine correspondences in 1.2 ms and reports best-in-benchmark accuracy plus usable translational velocity.
Canonical reference
Reducibility among combinatorial problems
Canonical reference. 89% of citing Pith papers cite this work as background.
52
Pith papers citing it
Background
89% of classified citations
citation-role summary
background 9
citation-polarity summary
roles
background 9representative citing papers
Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
Domain-specific macOS features enable an ML detector to reach 98.5% accuracy on 41k samples and 99.5% on 9k fresh samples, beating prior methods by 16-50%.
LLM2Ltac mines symbolic tactics from 11,725 Coq theorems using LLMs and integrates them into CoqHammer, improving proof rates by 23.87% on 6,199 theorems from four large verification projects.
Manifold k-NN generalizes DP-NNS to k-NN queries on manifold point clouds via a recursive successor-list property, delivering 1-10x speedups and full dynamic support.
A complete, axiom-free Lean 4 formalization of combinatorial curve neighborhoods for A1(1) has been achieved by encoding them as maximal vertices in degree-bounded reachable sets of the infinite dihedral moment graph.
Embedding CUDA Graphs in UCX for multi-path intra-node GPU communication yields up to 2.95x bandwidth improvement over single-path UCX on a four-GPU node for large messages.
GraphQLify automates REST-to-GraphQL migration via static source code analysis, delivering 100% type-safe conversions on 834 APIs and 2-4x faster performance than REST for multi-call workflows.
SoulNote enables multi-session GenAI songwriting for DHH users, producing measurable gains in self-insight, emotion regulation, and self-care attitudes.
RBE-Flow recasts dense cross-modal flow estimation as closed-loop recurrent Bayesian estimation on learned feature manifolds with uncertainty-adaptive updates and achieves SOTA on three registration benchmarks.
ConnectomeBench2 supplies a unified multi-species benchmark of expert proofreading labels and shows a single Vision Transformer achieving human-level performance on split and merge error tasks while providing calibration and distribution-shift diagnostics.
A multi-contrast self-supervised MRI reconstruction framework with end-to-end learned k-space partitioning produces higher-fidelity images than single-contrast self-supervised baselines on two public datasets.
Develops a bi-form framework unifying contrast and pre-contrast functions on torsion-full Lauritzen manifolds and constructs a canonical contrast bi-form on dually curvature-free cases.
EmbedFilter applies a linear filter derived from the LLM unembedding matrix to suppress high-frequency token influences in text embeddings, yielding improved zero-shot performance and inherent dimensionality reduction.
Echo-POSED learns an SO(3)×SO(3) pose representation via self-supervised equivariance to probe motion and invariance to cardiac phase from 2D slices of 3D echocardiography volumes, reporting 8.2° mean angular error in intra-patient guidance simulations.
Authors construct a parameterized algorithm for testing emptiness of limits of structured co-decompositions in FinSet^J for finite J.
Users entangle their lived experiences with AI predictions in menstrual tracking apps, leading to self-fulfilling prophecies, limited critical awareness from UI, and isolation for non-normative users.
A machine-checked Lean 4 formalization of Stokes' theorem on smooth singular cubes with true Fréchet pullback, chain-level extensions, and comparison to prior HOL Light work.
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.
Checksum Count Vectors enable robust similarity search to identify duplicate and variant legacy media recordings with high accuracy despite substantial data damage.
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
Zero-shot inversion-free flow method de-identifies skin images in under 20 seconds while preserving pathological features with IoU stability exceeding 0.67 using segment-by-synthesis and CIELAB decoupling.
citing papers explorer
-
Compositional Neural-Cyber-Physical System Verification in the Interactive Theorem Prover of Your Choice
Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
-
Formalizing $A_1^{(1)}$ Curve Neighborhoods in Lean 4
A complete, axiom-free Lean 4 formalization of combinatorial curve neighborhoods for A1(1) has been achieved by encoding them as maximal vertices in degree-bounded reachable sets of the infinite dihedral moment graph.
-
Stokes' Theorem for Smooth Singular Cubes in Lean 4: True Pullback, Bridges to mathlib4, and Chain-Level d^2=0
A machine-checked Lean 4 formalization of Stokes' theorem on smooth singular cubes with true Fréchet pullback, chain-level extensions, and comparison to prior HOL Light work.
-
Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.