Science & Mathematics

LLMs on edge devices are constrained by limited memory and bandwidth. Although 1.58-bit ternary weights greatly reduce model storage, long-context inference is increasingly bottlenecked by KV-cache traffic and attention. Existing accelerators also use separate datapaths for ternary linear layers and attention, incurring hardware and execution overhead. We present SPARTA, a sparse ternary LLM accelerator for efficient long-context edge inference. SPARTA integrates: (1) a phase-aware sparse dataflow exploiting heterogeneous sparsity across compute-bound prefill and memory-bound decode; (2) a unified compute fabric mapping ternary SpMM/SpMV and bit-serial attention onto shared processing elements to exploit zero-weight and zero-bit sparsity; and (3) an adaptive two-stage attention engine combining page-level Top-k selection to reduce K-cache accesses with token-level Top-p pruning to reduce V-cache traffic. SPARTA reduces KV traffic by 4.1-4.8x over full attention and 1.3-1.5x over a state-of-the-art sparse-attention scheme, with task-dependent quality loss. Compared with NVIDIA Jetson AGX Orin, SPARTA achieves 3.9x higher generation throughput and 8.3x higher end-to-end energy efficiency on average; versus AMD Ryzen 7 9700X, the gains are 5.0x and 81.7x. It also delivers 1.6-12.0x higher throughput, 2.0-4.2x higher energy efficiency, and 1.3-51.4x higher area efficiency than FIGLUT, TeLLMe, and MCBP.

Diffusion MRI (dMRI) provides information about white matter microstructure that can support brain age prediction. However, many existing prediction models use diffusion tensor imaging (DTI) scalar metrics that omit orientation information. Deep learning is increasingly used for brain age prediction, but conventional CNNs do not explicitly respect the geometric structure of orientation-dependent features. We present an interpretable brain age prediction framework that combines white matter fiber orientation distributions (WM-FODs) with an SE(3) (Special Euclidean group in 3 dimensions) equivariant CNN. The network operates directly on spherical harmonic (SH) coefficients of the FOD, preserving their transformation properties under rotation. Evaluation in 692 participants aged 36-90 years from the Human Connectome Project Aging dataset showed that the combined framework outperformed the evaluated DTI-based models and conventional CNNs. Averaging predictions from five cross-validation models yielded a mean absolute error of 3.54 years and Pearson's correlation of 0.958. Our results indicated that the performance advantage depended on combining WM-FODs with equivariant processing. Prediction accuracy was highest at a maximum SH order of Lmax = 2 and declined at higher orders. Tract-level occlusion, where each segmented tract was masked in turn, revealed age-dependent patterns of model sensitivity, with importance peaks in frontal projection pathways at 36-44 years, the fornix at 45-54 years, the callosal isthmus at 55-64 years, the middle cerebellar peduncle at 65-74 years, and the callosal genu at 75-90 years. These findings support rotation-equivariant processing of WM-FODs for accurate brain age prediction with anatomically interpretable model sensitivity.

Decision models enable software to select from predefined actions using natural language inputs. However, the external evidence that supplies facts for these decisions may also contain instructions that attempt to override the application's policy. We propose TrustJev, a framework combining protected policy scoring with bounded evidence corrections. A single Transformer backbone computes policy scores and a correction budget from trusted policy and candidates, then bounds evidence corrections by that budget. Paired supervision encourages stable predictions under instruction insertions that preserve task facts and changed preferences when edits change the correct answer. Authority supervision accommodates evidence when the policy alone cannot determine the decision. We evaluate a 0.6B implementation against 14 baselines on three datasets covering authentication, instruction hierarchy, and executable authorization rules. TrustJev achieves the highest mean Balance, the harmonic mean of accuracy on non-attack and attack inputs, exceeding the strongest baseline on each by 0.57-1.05 percentage points. In the authorization benchmark, it correctly answers all 32 attacks per source in a fixed pool for 95.77% of sources, compared with 80.98% for the strongest comparator. TrustJev maintains comparable inference memory and median latency, with additional overhead primarily during training.

Effective discrete representation learning with VQ-VAE serves as a fundamental component of modern autoregressive generative models. However, it is widely known to suffer from codebook collapse and inefficient code utilization. To address this issue, we propose FlowVQ, a simple yet effective alternative to standard vector quantization by formulating neural quantization as a joint modeling and clustering process. Specifically, we learn the latent space using a lightweight flow matching model alongside training, corresponding to a probability flow ODE that transports an often fixed well-behaved source distribution while preserving probability mass. Based on this, we define the codebook C_1 by transporting even-quantile partitioned prior codes C_0 from the source space through the learned flow, and obtaining the Voronoi centroids under the induced distribution, leading to a structured discretization. We evaluated on image tokenization and generation, as well as on two tasks requiring high-precision tokenization, demonstrating scalability and improved expressivity of the codebook with full utilization.

Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on explicit factual refutations or imperative instruction overrides. Modern aligned LLMs often arbitrate such conflicts conservatively, rejecting overt contradictions in favor of parametric memory or clean retrieved context while triggering input guardrails. We propose MONOLOGUE, a single-document poisoning framework based on Logic Hijacking without explicit refutation. Rather than disputing the ground truth, our method concedes it as an authoritative historical baseline before introducing the update, weaving a grounded record-correction narrative (e.g., dated institutional reattributions) that presents the counterfactual target as the most recent update. To prevent suspicious live writes, payloads are refined entirely offline via local multi-dimensional gated optimization, coupling automated text quality audits with surrogate behavioral verification. Evaluations across three benchmarks, three retrieval backends, and four open-weight generator regimes show that our method achieves the strongest overall attack efficacy among the evaluated single-document poisoning attacks.

Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback as soon as it arrives, even when it is delayed. In contrast, most modern deep learning systems rely on stored datasets, replay buffers, and retained contexts through which credit is later assigned. At high data rates, storing and revisiting past experience can be impractical under tight memory and computational constraints. This paper studies recurrent memory under a streaming learning constraint: the learner learns from experience as soon as it arrives without storing raw experience. We ask whether a streaming learner can maintain a state that remains useful for future prediction and control from delayed feedback. We introduce Streaming Recurrent Memory (SRM), a recurrent memory designed for the streaming setting which preserves information that may matter later while remaining trainable with one-step backpropagation through time (BPTT). SRM provides a streaming-compatible recurrence that is designed to recall past information by content or time, track elapsed steps, and compose transformations whose outcome depends on the order in which inputs are observed. Across controlled memory tasks and streaming applications, SRM learns effectively with one-step BPTT, outperforming recurrent baselines in associative recall and online language modeling while achieving near-perfect success in associative T-Maze with delayed rewards. These results suggest that fixing how inputs are stored in the recurrent state, while learning how that state is read out, enables effective streaming learning without long-range backpropagation.

Clean-image prediction ($x$-prediction) and noise prediction yield equivalent population-optimal denoisers, yet can perform very differently in finite diffusion networks. For noisy input $Y_t$ with noise standard deviation $σ_t$, a noise predictor $f_{\varepsilon,t}$ induces the clean-image estimate $\widehat X_1=Y_t-σ_t f_{\varepsilon,t}(Y_t)$. This reveals a noise-transmission burden: the predictor must preserve information needed to cancel the input corruption. Under Gaussian corruption of $d$-dimensional data, a linear input bottleneck of rank $r

Multi-agent large language model (LLM) systems can exhibit emergent behaviors through interaction, yet whether a similar phenomenon exists for reasoning alignment remains largely unexplored. We study whether agent interaction produces additional reference-grounded reasoning alignment beyond matched individual self-refinement, and introduce REMAP (Reference-Entailment-Matrix for Agentic Process), a framework that quantifies this effect through Semantic Coverage and interaction-specific alignment gains. Across diverse model families and two multi-hop reasoning benchmarks, we observe broadly positive interaction gains, particularly on reasoning content that depends on integrating evidence distributed across agents. These gains are consistently associated with independently measured peer-information recovery, while further analysis reveals composition-dependent heterogeneity effects and asymmetric information transfer across agent capability levels. Motivated by these findings, we further introduce a fact-level multi-agent communication framework that replaces full reasoning-trace exchange with compact, gap-aware, and selectively routed information. Our experiments show that compact fact exchange improves reasoning alignment and task performance while reducing communication overhead, whereas more selective communication exposes a trade-off between acquiring distributed information, retaining local content, and communication efficiency. Overall, our results show that collective emergent alignment can be quantified, linked to information-transfer patterns, and used to guide more effective multi-agent communication.

Humans exhibit biological sensitivity to safety-critical stimuli that can trigger defensive action. Across three models and two video benchmarks, we investigate whether similar responses emerge in vision-language-action models by examining their internal representations and action tendencies in response to visible hazards and harmful consequences. Our findings suggest that task execution may remain the default response even when danger is internally registered.

Efficient microarchitecture design space exploration (DSE) is critical for optimizing performance, power, and area trade-offs in modern out-of-order processors. While machine-learning-based DSE significantly reduces the cost of exhaustively evaluating large design spaces, existing methods still waste expensive simulations on Pareto-miss candidates that do not improve the Pareto frontier and repeatedly process redundant candidates during iterative exploration. In this paper, we propose PaFeDSE, a Pareto-feedback-guided microarchitecture DSE framework for efficient Pareto search. PaFeDSE leverages Pareto-hit feedback to prioritize candidates likely to improve the frontier and Pareto-miss feedback to suppress exploration of unpromising local regions, while filtering redundant candidates that remain low priority across iterations. Evaluated on SPEC CPU 2017 workloads, PaFeDSE requires up to 49.0% fewer simulations than the strongest prior baseline to reach target hypervolume levels, while achieving a 7.1x reduction in exploration overhead through adaptive candidate filtering.

Human behaviour models are increasingly used to provide simulated human interactions for training robots via reinforcement learning (RL). Existing approaches primarily evaluate these models according to how closely their generated behaviours resemble real human data, while their usefulness as training partners is less commonly assessed. This creates a potential objective mismatch: a model that performs well according to behavioural evaluation metrics may not necessarily provide useful training experiences for downstream robot policy learning. Across two human-robot interaction (HRI) domains, highway driving and object handover, we evaluate different types of human behaviour models using common generative-model evaluation metrics. We consider multiple human trajectory representations and compare the resulting evaluations with the downstream performance of RL policies trained using the corresponding models. We find that existing behavioural evaluation metrics do not consistently predict downstream policy performance across domains and trajectory representations, while their evaluations are sensitive to the choice of trajectory representation. We also show that even when the true testing behaviour distribution is known, training against a different distribution may yield better downstream performance than training directly against the true distribution.

Quantum software development is challenged by quantum-mechanical semantics and fragmented software development kits (SDKs), which complicate cross-SDK code translation and execution. In this paper, we propose an LLM-based approach for translating executable programs between high-level quantum SDKs. We develop a quantum-aware translation workflow whose prompt design and validation reflect quantum semantics and accommodate the version evolution of quantum ecosystems. We conduct a preliminary evaluation of 4 LLM configurations on 43 tasks, translating Qiskit programs to PennyLane and Q#. LLMs achieve a zero-shot Pass@1 of up to 72.33%, while one-shot prompting further improves the translation effectiveness. These results suggest potential for quantum code translation by LLMs.

Across social and behavioral research, measuring latent constructs can be challenging when target populations are small or difficult to reach. Recruiting additional respondents may be costly or infeasible, leaving researchers with limited data for estimating questionnaire factor structures. Yet item wording contains structural expectations before data collection, and whether these can improve small-sample estimation without replacing empirical validation remains unclear. We introduce the Semantic-Empirical Updating Framework (SEUF), which converts large language model paraphrases and embeddings, aligned with hypothesized item-factor assignments, into prespecified priors for Bayesian confirmatory factor analysis. We evaluated SEUF using a 38-item survey of 617 industrial-park stakeholders and two public surveys, FEVS and RIASEC. Semantic structure persisted after wording controls across all three instruments. With 50 respondents, SEUF achieved loading precision comparable to conventional CFA with 70-82 respondents, equivalent to 29-39% fewer respondents at the specified precision benchmark. Results showed lower loading errors and improved credible-interval coverage relative to conventional CFA in both public surveys. Gains were greatest when respondent data were limited, highlighting the value of semantic priors under information scarcity. By harnessing structural information already embedded in questionnaires, SEUF advances a more resource-efficient approach to measurement and opens new directions for study design and empirical inference in hard-to-reach populations.

Graceful degradation is a key mechanism employed by large-scale systems to handle overload conditions. Its importance has grown further as GPU-intensive LLM inference introduces persistent capacity constraints that cannot be addressed through provisioning alone. Common degradation approaches rely on service-level mechanisms such as load shedding and circuit breakers, or on feature-level switches (some manually controlled) to preserve availability and quality. While effective at protecting services, such approaches lead to untestable product states and thereby unpredictable product quality. We present HiLO (High Load Optimizer), an automated product-level degradation system designed to handle graceful degradation at scale. HiLO maps observed load to a product state lattice: a small set of pre-validated product states, partially ordered by degradation severity. Dependencies are resolved at design time enabling deterministic and continuous control without requiring runtime dependency discovery. The same abstraction applies unchanged across heterogeneous services, including GPU-intensive deep models, LLMs and their serving layers. At Microsoft, HiLO is deployed in Bing (serving over a billion monthly active users), where it manages on average two traffic surges per week across all datacenters, bounding OneDCG (relevance) drop to under 0.5 points (the operational target) even under sustained load exceeding 2$\times$ baseline peak. HiLO complements existing service-level protections with product-level coordination and makes product quality measurable, testable and predictable.

Recent multi-view Transformers (e.g., DUSt3R and VGGT) have advanced 3D reconstruction by scaling training data and model capacity from two views to many views and long sequences, subsuming the classical SfM/SLAM pipeline of feature extraction, matching, and pose estimation in a single feed-forward pass. Yet this subsumption hides the interfaces between pipeline stages---correspondences, geometry, and pose are entangled in a single forward pass, leaving supervised fine-tuning as the major path to improvement and offering no mechanism to correct predictions from geometric evidence at test time. We propose PosePlaner to close this gap by reviving the classical coupling between correspondences and pose via flow matching, treating pose refinement as a conditional generation problem that takes coarse geometric matches and initial pose as input condition and fuses the resulting pose hypotheses into a single refined estimate, providing a continuous, data-driven analog of RANSAC voting. Our method is trained efficiently on two-view data, yet serves as a periodic refiner for streaming n-view pose estimators with no retraining. Empirically, it corrects failures of feed-forward predictors, substantially improves correspondence-based solvers, and reduces accumulated drift in long streaming sequences.