Stories tagged science & research.
arXiv
arXiv:2609.25643v1 Announce Type: new Abstract: Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reasoners even with knowledge distillation (KD). We present Ladders-of-Thought (LoT), a framework that…
arXiv
arXiv:2609.00450v2 Announce Type: replace-cross Abstract: Block Quantization (BQ) enables efficient LLM inference by quantizing both weights and activations, but its design space remains underexplored. Through hardware-accuracy design space exploration, we identify block size as a key trade-off…
arXiv
arXiv:2609.25199v1 Announce Type: new Abstract: Lean Pool is a repository of formalized mathematics. It is grown, maintained and optimized by AI agents.
arXiv
arXiv:2609.25588v1 Announce Type: new Abstract: In this note, we show that the problem of checking, whether a sequence of bits is ordered, is not doable by 1-head 1-layer transformers but is doable by a 2-head 1-layer transformer. Unlike similar previous results, our results assume the model where…
arXiv
arXiv:2609.25555v1 Announce Type: new Abstract: Supervised approaches to quantum error mitigation learn a map from noisy circuit outputs to ideal ones, and therefore require the ideal outputs. Producing those ideal outputs demands noiseless classical simulation, whose cost grows exponentially with…
arXiv
arXiv:2603.03772v2 Announce Type: replace-cross Abstract: AI-driven analytics are increasingly crucial to data-centric decision-making. Executing relational and AI operators in separate runtimes prevents the database optimizer and runtime from coordinating operator ordering, model placement…
arXiv
arXiv:2609.24424v2 Announce Type: replace-cross Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict hand poses relative to the wrist, while global hand pose estimation also requires…
arXiv
arXiv:2609.26237v1 Announce Type: cross Abstract: We present the ABAI submission to COLIEE 2026 Task 1, case law retrieval, together with a controlled study of why it underperformed. The task suppresses the cited passages themselves, which removes much of the lexical overlap a retriever would rely…
arXiv
arXiv:2609.26342v1 Announce Type: cross Abstract: Residual Vector Quantization turns continuous representations into discrete, multi-level token sequences. Yet most methods operate in Euclidean space, despite the coarse-to-fine structure of the resulting codes and the latent hierarchies present in…
arXiv
arXiv:2609.26378v1 Announce Type: cross Abstract: Successful mobile manipulation requires coordinated base and arm motion while maintaining accurate spatial positioning. However, demonstration-trained policies can struggle to realise the intended base motion reliably, leading to spatial…
arXiv
arXiv:2609.25469v1 Announce Type: new Abstract: Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable external knowledge, yet their structural reliance on a dynamic retrieval pipeline introduces a…
arXiv
arXiv:2609.25408v1 Announce Type: new Abstract: Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to be computable without treatment-arm user exposure…
arXiv
arXiv:2608.28150v2 Announce Type: replace-cross Abstract: How much matrix rank is required to preserve every bounded value output of normalized softmax attention? We study the unrestricted maximum-row-\(\ell_1\) approximation rank \(r_\varepsilon(A)\), exactly the least rank achieving uniform error…
arXiv
arXiv:2609.06100v4 Announce Type: replace-cross Abstract: Verifiable rewards improve language models through reliable task-level feedback, but methods based on Group Relative Policy Optimization (GRPO) apply a sequence-level advantage uniformly across all tokens. This coarse credit assignment…
arXiv
arXiv:2602.02361v2 Announce Type: replace-cross Abstract: We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic…
arXiv
arXiv:2609.17521v2 Announce Type: replace-cross Abstract: Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods either require the full control schedule before generation…
arXiv
arXiv:2609.21997v2 Announce Type: replace-cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified, and collective outcomes inherit the model's training prior. We introduce Bayesian…
arXiv
arXiv:2609.22851v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding remains debated. Existing benchmarks often focus on narrow domains or evaluate…
arXiv
arXiv:2609.25165v1 Announce Type: new Abstract: In this report, we introduce \textbf{Ovis-Embedding}, a state-of-the-art omni-modal embedding family built on native integration of text, image, video, and audio. Instead of assembling separate modality towers, Ovis-Embedding uses a shared multimodal…
arXiv
arXiv:2609.24971v2 Announce Type: replace-cross Abstract: Agents today often take real-world actions that depend on long-term memory and context recall over time. However, most current memory benchmarks are built for a conversational question-answer format, where the question itself signals that…
arXiv
arXiv:2506.02153v3 Announce Type: replace Abstract: Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of…
arXiv
arXiv:2603.06884v2 Announce Type: replace Abstract: The agentic web marks a structural transition from a human-centered information network to a digital environment populated by artificial intelligence (AI) agents that perceive, decide, and act autonomously. As delegated action unfolds at machine…
arXiv
arXiv:2608.03699v4 Announce Type: replace Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish…
arXiv
arXiv:2609.04476v2 Announce Type: replace Abstract: Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computation, data reuse, storage, and movement. We introduce PerfReasoning, a benchmark that evaluates…
arXiv
arXiv:2609.16639v3 Announce Type: replace Abstract: Continual post-training of large multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in opposite directions. SFT gives explicit target supervision that learns a task from near-zero…
arXiv
arXiv:2311.04799v3 Announce Type: replace-cross Abstract: Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable pretraining methods. One notable advancement in this area is…
arXiv
arXiv:2511.02769v2 Announce Type: replace-cross Abstract: Many molecular Transformers lack probabilistic latent variables for posterior inference and latent interpolation. We introduce STAR-VAE, a SELFIES-encoded, Transformer-based, AutoRegressive Variational AutoEncoder combining a bidirectional…
arXiv
arXiv:2609.24446v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or…
arXiv
arXiv:2608.25581v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allowing users to inspect the concepts underlying a prediction and…
arXiv
arXiv:2512.07309v2 Announce Type: replace-cross Abstract: Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness…