Search: “evaluation”

arXiv:2607.21978v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have been widely adopted in large language models, yet parameter-efficient fine-tuning (PEFT) for MoE models rema

arXiv:2607.21634v1 Announce Type: new Abstract: Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence r

arXiv:2607.22083v1 Announce Type: cross Abstract: We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-

Nice little insights on doing autoresearch with coding agents. Hand a coding agent a dataset, an eval script, one editable file, and no supervision. That's autoresearch and it tries to optimize the nu

arXiv:2607.21975v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) optimizes J(B,A)=mathcal L(W_base+sBA) over two adapters B in R^{m imes r} and A in R^{r imes n} that form a low-rank update

arXiv:2607.22119v1 Announce Type: cross Abstract: Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental refer

arXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor

arXiv:2607.22486v1 Announce Type: new Abstract: Control valve stiction is a common cause of unwanted oscillations and poor control-loop performance in industrial processes. Data-driven methods can aut

arXiv:2607.21665v1 Announce Type: new Abstract: Proactive service assurance in O-RAN requires predicting per-slice SLA violations before they occur. The prediction model must be auditable by operators

arXiv:2607.22518v1 Announce Type: cross Abstract: In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to p

arXiv:2607.21820v1 Announce Type: cross Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same d

arXiv:2507.16257v2 Announce Type: replace Abstract: Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in divers

arXiv:2607.22293v1 Announce Type: new Abstract: Medical multimodal large language models (MLLMs) are increasingly expected to perform complex image understanding tasks, yet their reliability is often

arXiv:2607.21772v1 Announce Type: cross Abstract: Near 1310 nm photonic-crystal surface-emitting lasers (PCSELs) are attractive narrow-beam sources for optical communication and sensing, but their fin

arXiv:2607.18292v2 Announce Type: replace-cross Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability. The knowledge-gap account --

arXiv:2607.21885v1 Announce Type: new Abstract: Coarsening-based training for graph neural networks (GNNs), i.e. training on coarsened graphs rather than the original large ones, has become a promisin

arXiv:2607.21787v1 Announce Type: new Abstract: Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisiti

arXiv:2607.22043v1 Announce Type: new Abstract: Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of th

The performance of AI agents depends not only on the underlying models but also heavily on their “harness”—the surrounding architecture that supplies context, state management, action execution, and t

arXiv:2607.22529v1 Announce Type: new Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fund

arXiv:2607.22034v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor li

arXiv:2607.21802v1 Announce Type: new Abstract: Social appropriateness in human-robot interaction (HRI) is not universal: different people can judge the same robot action differently in the same situa

arXiv:2607.11204v2 Announce Type: replace Abstract: Onboard quadruped inspection systems often share limited compute between perception and navigation, reducing the rate at which event-triggered contr

arXiv:2509.22352v3 Announce Type: replace Abstract: Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death. Un

arXiv:2607.22491v1 Announce Type: new Abstract: Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit. We introdu

arXiv:2607.22304v1 Announce Type: new Abstract: Synthetic data augmentation in speech is common practice for linguistic tasks like ASR, but has seen far less work for paralinguistic ones, especially c

arXiv:2506.20302v2 Announce Type: replace Abstract: Images captured in challenging environments often experience various types of degradation, such as noise, color cast, blur, and light scattering. Th

arXiv:2607.21613v1 Announce Type: cross Abstract: We investigate where and how transformer-based language models commit to predictions in multiple-choice question answering. We identify the _Hard Deci

arXiv:2601.19618v2 Announce Type: replace Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is t

arXiv:2607.21887v1 Announce Type: cross Abstract: Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferat

arXiv:2607.21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low

We're proud to join @NVIDIA and the Open Secure AI Alliance. To support open source models, we're contributing our research on measuring the trustworthiness and security of open source models. Closing

arXiv:2607.21792v1 Announce Type: new Abstract: One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's licenses and/or booking

arXiv:2505.19212v2 Announce Type: replace Abstract: Recent advances in LLMs have enabled their use in complex agentic roles, involving decision-making with humans or other agents, making ethical align

There is a lot of buzz around running 100B parameter models on cheap local hardware using ternary (1.58-bit) quantization like Microsoft's BitNet architecture. The theoretical hardware shortcuts are i

I'm a software engineer who mainly builds softwaes/applications, and I'm starting to work on machine learning projects. Since ML workloads often require GPUs, I know services like Google Colab and Kag

--> .abbel-fig { display: block; text-align: center; margin: 2.4em 0; line-height: 1.4; max-width: 100%; } .abbel-fig img { display: block; margin: 0.65em auto 0; height: auto; max-width: 100%; } /* I

Hi everyone! Over the past five months I've been working on DKV (DifferentialKV), an open-source project exploring KV-cache compression for long-context local LLM inference. The goal is to reduce KV-c

I’ve spent the past month trying to find the point where an extremely small TTS model stops feeling like a size experiment and starts feeling genuinely useful. Today I’m releasing Inflect v2, with two

arXiv:2607.20700v1 Announce Type: cross Abstract: The operation of blockchain is governed by consensus algorithms (CA). Several consensus mechanisms require significant computational power, while othe

arXiv:2607.20453v1 Announce Type: cross Abstract: Large language models show promise for clinical prediction, but zero-shot performance on specialized tasks is limited by incomplete domain knowledge,

arXiv:2607.21203v1 Announce Type: new Abstract: Description logic programs are a powerful formalism for combining rules with ontologies. The well-supported semantics for description logic programs ens

arXiv:2607.18317v2 Announce Type: replace-cross Abstract: We present TTSYoruba, a rule-based concatenative diphone speech synthesizer for Yoruba, deployed at online as part of the YorubaName.com open

arXiv:2607.20742v1 Announce Type: new Abstract: Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicabilit

arXiv:2607.21162v1 Announce Type: new Abstract: Outsourced Transformer inference exposes clients to model substitution and incomplete execution, while direct replay removes the computational benefit o

arXiv:2607.20452v1 Announce Type: new Abstract: Modern software quality assurance demands intelligent, autonomous systems capable of adaptive decision-making across distributed cloud environments. Thi