Nothing here yet
Underwater vessel recognition is limited by scarce training data and small public benchmarks. This paper introduces ONCship, a 4521-hour corpus curated from Ocean Networks Canada hydrophones and Automatic Identification System vessel metadata. It evaluates domain-specific self-supervised pre-training, supplementary supervised fine-tuning, and MMSI-Level individual vessel classification, showing that scale and metadata can improve representations even though downstream gains are architecture-dependent and uneven.
Potato leaf diseases such as early and late blight reduce yields in Ethiopia, where farmers often lack access to laboratory diagnosis. This study develops a lightweight convolutional neural network to classify healthy, early-blight, and late-blight leaves, training on 2,215 PlantVillage images and testing on 247 smartphone photos collected from local farms. The central claim is that a 1.70 MB model can achieve high accuracy while remaining efficient enough for deployment on low-resource hardware.
Most robot VLAs rely on wrist cameras for manipulation detail, which narrows scene coverage and adds hardware complexity. FoveaVLA removes that dependency by teaching a π0.5-based policy to predict future interaction regions, cropping high-resolution 'foveal' patches from external stereo views to recover fine gripper-and-object detail. Post-trained on DROID with RoboInter annotations, the model achieves 77.1% overall real-world success with two external RGB-D views versus 52.1% for the wrist-equipped baseline. The idea is biologically grounded and architecturally clean, though the evaluation scale and claims about learning from human videos remain tentative.
Fairness-weighted federated learning deliberately inflates updates from high-loss clients, but under an update-only interface a server cannot tell legitimate amplification from adversarial scaling. This paper identifies that $q$-fair loss scaling preserves the class-mixture structure of honest updates while warping their coefficient constraint from a unit-sum simplex to a radial nonnegative cone. Building on this geometry, FUSE uses a small trusted labeled set to recover latent coefficients, screens submissions jointly for radial scale and cone consistency, and renormalizes the aggregate to protect both robustness and fairness.
Most research on test-time compute treats the model as fixed and asks how to allocate extra inference tokens. This paper instead asks whether a model can be post-trained to use a given compute budget more effectively. The authors identify compute-responsive (CR) problems—those that flip from complete failure to success under additional blind re-solving or audit-based revision—and show that supervised fine-tuning on these examples shifts the compute–accuracy frontier across budgets from 512 to 4,096 tokens and generalizes across model families.
Training deep networks without normalization remains difficult, and relating their trainability to the exact geometry of the loss surface is rarely attempted. This paper proposes a projective polynomial activation $f(z)=z+\lambda z^3$ paired with either an $\ell_2$ projection onto the unit sphere or an unnormalized identity path, and studies it at two scales: networks that train to depth $100$--$300$ on MNIST, and tiny algebraic versions whose square-loss critical points are solved exactly via Gröbner bases and numerical irreducible decomposition. The point is to derive concrete design, initialization, and diagnostic rules from the small model's geometry and validate them at depth.
Multimodal code intelligence demands programs that are correct, well-structured, and visually faithful, yet existing training signals are either too coarse or confined to single tasks. This paper introduces PrismaForge, which synthesizes per-instruction evaluation rubrics that separately assess code-level and visual-level criteria, then uses them to filter training data and reward reinforcement learning. The resulting dataset, PrismaCoder-2M, and the trained 9B and 35B models advance the open state of the art and compete with proprietary systems on charts, webpages, and scientific graphics.
Deploying LLMs as agents requires respecting runtime-specific execution contracts, yet standard training leaves harness semantics implicit in action trajectories. This paper introduces Harness Policy Distillation (HPD), which replays reference trajectories through the target harness to compile control-state documents, uses harness verification to filter teacher actions, and jointly trains a shared model on native action prediction, document-conditioned action prediction, and document reconstruction. On TRAJECT-Bench with the Pi harness, HPD lifts Qwen3-8B task success from 3.09% to 22.98% and substantially outperforms supervised, RL, and standard distillation baselines.
Average-reward reinforcement learning with options models continuing hierarchical tasks, but before this paper there were no finite-time convergence guarantees for option-based Q-learning in that setting. The authors prove that multi-step (J-step) inter- and intra-option Bellman operators contract in the span seminorm, design corrected synchronous multi-step estimators, and derive the first $\widetilde{\mathcal{O}}(1/k)$ mean-square convergence rates for average-reward option Q-learning. The results extend to hierarchical reward machines and are supported by small-scale tabular experiments.
Speech Emotion Recognition (SER) models and Audio LLMs often suppress vocal emotion when it contradicts transcribed text—a bias the authors label Semantic Dominance. To probe this, they introduce ASPIRE, a fully synthetic benchmark of adversarial audio-text pairs generated via EmotiVoice, and propose ACR-Net, a dual-stream Whisper-based architecture that uses a Contrastive Decoupling Loss to push conflicting acoustic and semantic representations toward orthogonality. The work claims state-of-the-art Acoustic Accuracy on both adversarial and standard congruent datasets.
Consensus research has expanded from human social networks to multi-agent LLM systems, yet it remains unclear how language models coordinate when their preferences conflict. This paper adapts the Network Consensus game—where agents must agree on one of two colours despite receiving different payoffs for the agreed colour—to evaluate seven LLMs under varying network topologies and communication regimes. The authors find that open-source models reach consensus far less often than humans and usually require global messaging to do so, whereas ChatGPT 5.6-sol succeeds even with restricted communication through lower stubbornness and stronger majority-following. The work matters because it directly challenges the assumption that LLMs can serve as drop-in proxies for humans in social simulations or collective decision-making architectures.
This paper investigates how Retrieval-Augmented Generation affects question answering across five South Asian languages. The authors construct a Wikipedia-based multilingual dataset, generate questions with Qwen 3 32B, and compare non-contexted, contexted, and RAG-based answering using four LLMs. They find that RAG improves QA unevenly—substantially aiding non-popular cultural questions in Bangla and Tamil while underperforming direct contexted answering in Hindi and Nepali—suggesting that retrieval quality and language-specific data alignment matter more than the choice of RAG framework.
This paper studies policy optimization for long-horizon software-engineering agents that learn from sparse binary test outcomes. The core idea is a training recipe—dubbed SPO++—that combines the Muon optimizer with single-rollout asynchronous updates, truncated importance sampling (TIS), token-averaged loss, and auxiliary length/tool-error penalties. The authors claim this combination achieves higher training success than SPO baselines on repository-level issue resolution for two model families, suggesting Muon is critical for long-horizon RL.
Doc2Harness evaluates whether frontier LLMs can engineer a coding-agent harness from scratch, a capability that existing SWE benchmarks ignore by holding the harness fixed. The benchmark asks a build model to generate a complete harness from a development document and an interface-only skeleton, then evaluates it deterministically with a scripted mock model across $328$ black-box test cases. The results reveal a $26$-point performance gap between the best and worst models, with even the strongest scoring only $53.05\%$, suggesting substantial room for improvement in long-horizon infrastructure construction.
Document understanding has been evaluated through isolated silos—layout detection, OCR, reading order, and image captioning—making it impossible to audit whether a single coherent page parse exists. This paper proposes Read-Parse-Describe, a unified benchmark built from 2,402 ACM scientific documents that forces models to jointly output bounding boxes, semantic labels, reading order, recognized text, caption links, and alternative-text descriptions for visual elements. To combat spatial drift in compressed vision-language tokens, the authors introduce SARA, a lightweight residual adapter that re-injects crop-aligned multi-layer visual features into frozen VLMs.
Current social agent benchmarks reward fluent conversation but ignore whether agents actually reach valid plans that respect hidden constraints. This paper introduces HICO-Bench, a benchmark where two agents with private information must coordinate verifiable outcomes, and PaCPO, a reinforcement learning method that redistributes terminal rewards across turns by checking tentative plans against paired worlds. The work matters because it reveals that high LLM-judged conversation ratings frequently mask infeasible or unsupported agreements, and provides a concrete credit-assignment mechanism to train agents on verified social outcomes rather than just dialogue style.
Tabular foundation models learn to predict from in-context examples without task-specific fine-tuning, but dense architectures apply the same computation to every feature regardless of statistical context. OrionMoE-Small attacks this limitation by inserting a dataset-conditioned mixture-of-experts layer along the feature axis of a dual-axis Transformer, allowing the model to route different features to different expert networks based on both local token content and a global dataset register. If the sparse design truly helps, it could offer a principled way to scale tabular models by allocating computation heterogeneously; however, the paper never proves the MoE itself is responsible for the gains.
The paper studies how much context a Transformer must retain to perform in-context temporal-difference (TD) policy evaluation without parameter updates. Existing theoretical constructions store the full trajectory, costing Θ(Nd) memory. The authors prove the intrinsic limit is the Krylov dimension k_L, construct a fixed-parameter attention network that compresses raw transitions to Θ(nk_L) registers, and give tight worst-case approximation error Θ(γ^m max{1,1/(m(1−γ))}) when the context falls below k_L.
LLM entity extraction from full-length documents is widely deployed but its failures are poorly diagnosed. This paper runs a preregistered audit of two low-cost LLMs and a flagship control on 315 real-world cyber-threat-intelligence reports, finding that most false positives are background mentions rather than hallucinations, and that confidence signals can rank outputs for human review but cannot verify truth against relation-level counterfactuals. The results set a concrete deployment boundary for any high-stakes pipeline that triages extraction by confidence.
MUCO proposes manipulation units (MUs) to decompose long-horizon robot manipulation into reusable, verifiable sub-operations. Each MU carries a local goal, an initiation condition, and observable success/failure criteria; the MUCO framework matches MUs to specialist policy executors from a frozen capability registry, enables local retry and fallback, and avoids replaying already-verified prefixes. The conceptual goal is to reduce data-collection costs, enable cross-task reuse, and contain failures without joint training or shared backbones. The critical caveat is that the submitted preprint contains almost no quantitative results.