arXiv:2407.04277v2 Announce Type: replace Abstract: Pedestrian detection in conventional frame-based imaging often suffers from limited temporal responsiveness and substantial data redundancy. Inspired by the biological retina,…
arXiv:2603.12937v2 Announce Type: replace Abstract: Establishing accurate point-to-point correspondences between non-rigid 3D shapes remains a critical challenge, particularly under non-isometric deformations and topological noise. Existing functional…
arXiv:2512.03042v3 Announce Type: replace Abstract: We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions. Unlike benchmarks that…
arXiv:2606.25842v2 Announce Type: replace Abstract: Existing multi-modal large language models (MLLMs) face significant challenges in processing long video sequences due to strict input token limitations. As…
arXiv:2604.26283v4 Announce Type: replace Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during…
arXiv:2607.00736v2 Announce Type: replace Abstract: Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing…
arXiv:2510.09517v2 Announce Type: replace Abstract: Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do not reflect…
arXiv:2607.01431v1 Announce Type: new Abstract: We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM…
arXiv:2607.02510v1 Announce Type: cross Abstract: Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when…
arXiv:2607.01420v1 Announce Type: new Abstract: As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust…
arXiv:2607.02266v1 Announce Type: cross Abstract: Most data-mixing methods assume the corpus has already been partitioned into groups, and the choice of those groups determines what a…
arXiv:2607.01392v1 Announce Type: new Abstract: Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions.…
arXiv:2607.01236v1 Announce Type: new Abstract: As LLM agents gain increasing access to powerful tools, ensuring that their actions are aligned with the user's intent becomes critical.…
arXiv:2607.01388v1 Announce Type: new Abstract: Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought (CoT)…
arXiv:2607.01345v1 Announce Type: new Abstract: Turn-taking naturalness is central to full-duplex spoken dialogue systems, yet its automatic evaluation remains limited. Existing evaluations often rely on human…
arXiv:2607.01152v2 Announce Type: replace Abstract: Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence.…
arXiv:2607.01237v1 Announce Type: new Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high…
arXiv:2607.01238v1 Announce Type: new Abstract: Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapping between…
arXiv:2607.01239v1 Announce Type: new Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE…
arXiv:2607.01241v1 Announce Type: new Abstract: Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is…
arXiv:2607.01240v1 Announce Type: new Abstract: Count-based F1 is widely used as a proxy for LLM error-detection quality, but this paper shows that it can rise dramatically…
arXiv:2607.01293v1 Announce Type: new Abstract: We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text…
arXiv:2607.01245v1 Announce Type: new Abstract: We introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension…
arXiv:2607.02032v1 Announce Type: cross Abstract: Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation can…