Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.07962v1 Announce Type: cross Abstract: Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neu...
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
arXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-q...
The paper introduces a new evaluation setting called penalty‑framed no‑valid‑option MCQA, where multiple‑choice questions may contain no correct answer. By removing the correct option from the MMLU‑Pro mathematics subset and allowing models to either pick an option or abstain, the authors penalize forced‑choice responses that are invalid. Experiments reveal that even models with high standard MCQA accuracy can still produce invalid forced‑choice answers, indicating that traditional accuracy metrics miss an important aspect of model reliability.
arXiv:2610.08155v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by en...
The paper introduces Quantizer‑Aligned Recalibration (QuAR), a single‑pass test‑time adaptation technique for quantized vision transformers that does not require backpropagation or parameter updates. QuAR recalibrates activations at the input of frozen quantizers by aligning per‑channel statistics with the source calibration, thereby correcting the distorted code distribution caused by distribution shift. On ImageNet‑C, QuAR outperforms state‑of‑the‑art backprop‑free methods across 3‑, 4‑, 6‑, and 8‑bit precisions, achieving higher accuracy, lower latency, and minimal memory overhead while maintaining performance across diverse shift scenarios.
arXiv:2610.08388v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on kno...
arXiv:2610.08400v1 Announce Type: cross Abstract: Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to ge...
The paper presents a new multi‑turn benchmark of 423 conversations with 1,661 labeled turn‑states to study when language models should refrain from answering. It shows that probes for unanswerability transfer well across datasets that share the same underlying signal, but fail to generalise to other forms of epistemic uncertainty. While a calibrated probe can identify underspecified turns more accurately than chance, it does not consistently improve overall generation quality compared to standard methods.
arXiv:2610.08513v1 Announce Type: cross Abstract: LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to faithfully simulate human in...
arXiv:2610.08537v1 Announce Type: cross Abstract: In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would...
arXiv:2610.08559v1 Announce Type: cross Abstract: Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports...
arXiv:2610.08622v1 Announce Type: cross Abstract: System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troub...
arXiv:2610.08659v1 Announce Type: cross Abstract: Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-bas...
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Pri...
arXiv:2610.08760v1 Announce Type: cross Abstract: Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Br...
arXiv:2610.08782v1 Announce Type: cross Abstract: Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize i...
arXiv:2508.16821v2 Announce Type: replace Abstract: We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinfo...
arXiv:2511.20471v3 Announce Type: replace Abstract: Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively un...
arXiv:2511.20510v3 Announce Type: replace Abstract: Molecule generation from extremely limited training data is a key challenge in drug discovery. Existing fragment-based methods are more suitable th...