CS Paper Radar

Weekly top 20

2026-W36 Aug 31 – Sep 06, 2026

Ranked from 4,110 papers submitted on 7 days. Each research area gets slots in proportion to its share of this week's papers (at least one), filled by score; near-duplicates are removed. Why

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works
1

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

cs.LG cs.CL ·2026-08-31 ·Boryeong Cho, Sumyeong Ahn, Se-Young Yun
top venuebenchmarkcode/data
Abstract · Findings of EMNLP 2026; Code is available at https://github.com/VennTum99/PLC-DPO

Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data often violates this assumption, leading to reversed, weak, or ambiguous labels that cause harmful policy updates. To address this, we propose Posterior Label Correction DPO (PLC-DPO) to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case. The key idea is to use the calibrated policy-reference margin as online evidence to take appropriate correction actions. This reframes noisy preference learning as actively correcting supervision direction and strength rather than merely filtering suspicious examples. Across 57 dataset-model-benchmark cells, PLC-DPO obtains the best mean win rate against DPO (60.5 vs. 55.5 for the next-best method). Injected-noise and tie stress tests, human disagreement analysis, and self-confirmation diagnostics further show that the routing remains stable and distinguishes flipped from weakly directional pairs.

0.89
2

What Attention Recalls and Recurrence Controls in Hybrid Language Models

cs.CL ·2026-09-03 ·Kirill Afendulev, Alexey Dontsov, Elena Tutubalina, Anton Korznikov
top venuecode/datahighly cited
Abstract · Accepted to Findings of EMNLP 2026. 13 pages, 3 figures, 8 tables. Code: https://github.com/kirillTerra/split-prefill

Hybrid language models combine attention with a fixed-size recurrent state, but the role of each channel remains unclear. We introduce two cache-level interventions. Split-prefill keeps only the KV cache or only the recurrent state from a prefilled context, then generates an answer. State-swap pairs the KV cache from one context with the recurrent state from another in a single forward pass. On Qwen3.5 and Falcon-H1, the two channels split sharply by function. Exact retrieval survives only through attention (64-98% of full accuracy) and collapses to zero through recurrence. Output language and persona reverse the pattern: both survive recurrence (70-80% and 3-5x) while KV-only drops to ~1% language accuracy. State-swap confirms this causally: the answer takes its value from the KV side and its language from the recurrent side. Recurrent-only generation also accepts words that were never in the context but share meaning or parts with seen items. Attention provides a lookup over what was said; the recurrent state shapes how the model says it next.

0.85
3

Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis

cs.CV ·2026-09-02 ·Subash Khanal, Yangzhi Cui, Daniel Cher, Eric Xing, Brian Wei +2 more
publishedbenchmarkcode/data
Abstract · Accepted to SIGSPATIAL 2026: Application Track (Oral)

Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail within wide coverage. Current generative models of satellite imagery, however, operate along a single axis: they either zoom to enhance a single tile's resolution or pan to extend imagery at a fixed scale. As a result, no existing method produces a complete pyramid that stays consistent across both scale and space, where a high-zoom tile must agree with the coarse context it refines and with the neighbors it meets. Motivated by this gap, we introduce a new task, multi-scale tile completion: given a sparse set of seed tiles at arbitrary zoom levels and positions, synthesize a complete, uniform quadtree that is globally consistent across both scale and space. We approach this task with Genesis, a generative engine that brings both axes together by composing two specialized operators over the quadtree: a vertical super-resolution model and a horizontal mask-based outpainting model, producing pyramids that are consistent across zoom levels and seamless across neighboring tiles. Each operator achieves state-of-the-art results on its subtask, and the engine propagates sparse seeds into seamless, multi-resolution maps from any initial configuration. To evaluate the task and benchmark Genesis, we introduce dense500, a fully observed multi-scale pyramid dataset spanning diverse geographic regions, together with a suite of pyramid-level metrics. Code, models, and our dataset are available at https://github.com/mvrl/genesis.

0.83
4

Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation

cs.CL cs.AI ·2026-09-03 ·Giulia Pucci, Ruizhe Li, Arabella Sinclair
top venuecode/datahot direction
Abstract · EMNLP 2026 Findings

This paper investigates structural priming in language model (LM) production, examining how preceding structural context influences sentence completion. While prior work has demonstrated priming effects in comprehension of structural alternations, it remained unclear whether these persist in production, where, when generating, an LM samples from many possible continuations at each step. We address this question through a series of controlled sentence-completion experiments on dative constructions. In line with prior work, we find that LMs are susceptible to structural priming, particularly in sentences that are semantically coherent. In terms of priming magnitude, we find that while there is a greater relative increase of double-object datives against our baselines, in line with inverse frequency effects, there is a larger absolute increase in prepositional-objects, the more frequently produced construction. Finally, we not only observe that structural priming is boosted by lexico-semantic coherence, but that structurally primed completions display greater levels of lexico-semantic repetition. Taken together, our evidence supports the view that structural priming in LMs operates across multiple levels of linguistic representation, facilitating, and facilitated by syntactic, lexical, and semantic alignment. Code: https://github.com/the-context-lab/primedproduction.

0.83
5

Blackbox Small-Signal Modeling of Grid-Connected Inverters in Asymmetrical Power Grids

eess.SY ·2026-09-01 ·Airan Frances, Dionisio Ramirez, Javier Uceda
top venuehighly cited
Abstract · 11 pages, 14 figures, IEEE TRANSACTIONS ON POWER ELECTRONICS, VOL. 38, NO. 10, OCTOBER 2023

Power electronic converters are envisaged to be key enablers of modern electric power distribution systems. Grid-connected three-phase inverters are widely used in Smart Grids and microgrids, but also in standard grids. They provide controllability and dynamic decoupling capabilities, which are fundamental in the integration of renewable sources and storage systems and in specialized applications such as FACTS. Nevertheless, power electronics-based systems can exhibit dynamic interactions, which may lead to power quality issues. Although the electrical model of each element of these systems is important for their system-level analysis, they are rarely available. Blackbox modeling strategies are useful for obtaining behavioral models of commercial electronic converters. Most blackbox modeling strategies are focused on dc-dc electronic converters; however, some works have extended these concepts to three-phase converters by means of the dq framework, under the assumption of symmetrical and balanced conditions. This work proposes a new structure in the sequence domain to represent the dynamic behavior of grid-connected commercial converters in asymmetrical conditions. Experimental tests have been performed on a three-phase inverter to identify its blackbox model and its performance has been validated during an asymmetric voltage sag.

0.82
6

Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection

cs.AI cs.LG ·2026-09-03 ·Weijie Liu, Running Zhao, Wenhao Yuan, Jinfeng Xu, Zhanfeng Xu +2 more
top venuecode/data
Abstract · Accepted to EMNLP 2026 Main Conference. Dude is now open-source and available at https://github.com/VinnyLiu0817/Dude

LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.

0.82
7

Aerodynamic Shape Design Space Exploration with Deep Latent Diffusion Model

cs.CE ·2026-09-01 ·Zhen Wei, Edouard Dufour, Colin Pelletier, Michaël Bauerheim, Pascal Fua
publishedbenchmarkcode/datahot direction
Abstract · This is the authors' postprint of the AIAA Journal article https://doi.org/10.2514/1.J066320. Data, code and agentic skill demo: https://git…

We propose DiffGeo, a latent space diffusion-based generative framework for aerodynamic design space exploration under extreme data scarcity. DiffGeo combines a learned latent space model for automatic shape parameterization, with a diffusion sampler to directly generate novel, geometry-valid and controllable designs. We validate the approach on a series of case studies: (i) a 2D airfoil generation benchmark, where DiffGeo's latent diffusion model is compared against GAN- and VAE-based baselines in terms of sample quality, diversity and constraint adherence under limited data; (ii) integration into a surrogate-based optimization pipeline, where DiffGeo's conditional sampling produces task-informed airfoil data that improve both surrogate modeling and optimization performance; and (iii) extension to 3D turbomachinery blade prototyping, where DiffGeo generates realistic and high-performance blade geometries from a small set of reference designs. Throughout these investigations, DiffGeo achieves high-quality and diverse shape generation with at least an order of magnitude less data than alternatives, decouples geometry representation from design targets for flexible reuse, and seamlessly incorporates complex design constraints via energy-based conditioning. These capabilities demonstrate DiffGeo's potential to enhance early-stage design by automating design space exploration--improving efficiency, expanding design diversity and embedding engineering knowledge through controllable guidance.

0.81
8

Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT

cs.CL cs.CYcs.LO ·2026-09-03 ·Zikai Zhou, Yufei Jin, Yilin Xu, Yu-Chiang Wang, Chieh-Ju Chao +1 more
top venuecode/data
Abstract · Accepted to EMNLP 2026 (Main Conference). 46 pages, 6 figures, 28 tables. Code and prompts: https://github.com/stanford-oval/clinical-trial-…

Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions. We introduce VERDICT, an LLM-based agent that translates a decision task, its constraints, and its policy into Satisfiability Modulo Theories (SMT), then derives the decision with SMT and MaxSMT solvers -- so policies are applied consistently and decisions are accountable by construction. Across a SIGIR 2016-derived dataset and TREC 2021, VERDICT achieves the strongest decision accuracy among LLM-only and neurosymbolic baselines, applies policies with perfect consistency, and produces clinician-preferred rationales grounded in explicit assumptions and pivotal conditions, with improved counterfactual self-faithfulness.

0.81
9

The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA

cs.LG ·2026-09-02 ·Samuel Larson
published
Abstract · Accepted at the ICML 2026 Mechanistic Interpretability Workshop, https://openreview.net/forum?id=Spof4PusVI. 9 pages. Corrects a data-entry …

Continuous chain-of-thought models compress reasoning into latent tokens. Matrix-valued variants, which route each latent token through a d x d matrix bottleneck, introduce rank as a single-sample structural observable on the latent matrix Z. If matrix latents carry parallel reasoning paths via superposition, rank should track them, and truncating Z to low rank should hurt accuracy on tasks whose solutions plausibly require multiple components. Across four training regimes of a matrix-CODI model (three on ProsQA, one on GSM8K-Aug below the learning threshold), the rank-k projection ablation curve is flat to within 0.6 percentage points. A three-seed replication yields 81.0 +/- 2.0 percentage points accuracy while the final effective rank of Z spans {4, 12, 13}; the loss does not reward any particular rank. To test whether rank-blindness arises from the flatten-then-project readout alone, we trained four readouts: a bilinear reparametrization, a bilinear-plus-GELU readout nonlinear in Z, an SVD-augmented readout feeding singular values through an MLP, and a quadratic readout in Z Z^T. All four rank-k curves remain flat (Spearman p-values 0.63, 0.14, 0.82, 0.46). The flat curves persist for readouts nonlinear in Z. A linear probe on Z underperforms a raw pretrained hidden state at target prediction (AUC 0.673 vs. 0.846). A negative control on vanilla GPT-2 SFT (no matrix bottleneck, no Z, three seeds, n=500) reproduces a flat rank-k curve under the same intervention paradigm with pooled-mean range 0.20pp, and a random-h sensitivity floor lands at the same accuracy: the rank-k ablation alone conflates rank-blindness with position-irrelevance.

0.81
10

Prior-Guided Implicit Neural Representations for Single-Subject Diffusion MRI Super-Resolution

eess.IV cs.CV ·2026-09-01 ·Abdulkader Ghandoura, Marsil Zakour, William Consagra, Yogesh Rathi
publishedcode/data
Abstract · Accepted at the British Machine Vision Conference (BMVC) 2026. 16 pages, 5 figures, 2 tables. Project page: https://abdulkaderghandoura.gith…

Resolving complex fiber geometries in brain white matter requires high-resolution diffusion MRI at the cost of long acquisition times. This leads many clinical protocols to opt for low-resolution scans, making downstream microstructure estimation and tractography challenging. Implicit neural representations (INRs) can model the diffusion signal continuously, enabling native single-subject super-resolution by querying the network at arbitrary spatial coordinates, yet existing methods often suffer from long training times and lack a mechanism to incorporate anatomical priors to regularize super-resolution by constraining the space of plausible reconstructions. To address these limitations, we propose a novel transfer-learning framework that pre-trains an INR on a high-resolution template and then adapts it to subject-specific scans via registration and fine-tuning. For $4\times$ through-plane super-resolution from 5 mm to 1.25 mm on Human Connectome Project (HCP) data, our method reduces NRMSE by 36-49% and increases FSIM by 24-43% over a recent baseline with $6\times$ faster training, outperforming competing INR-based methods across both image quality and domain-specific metrics. Code is available on the project page at https://abdulkaderghandoura.github.io/research/msc-thesis/ .

0.81
11

Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech

cs.CL cs.SD ·2026-09-01 ·Che Hyun Lee, Sangkwon Park, Donghun Kang, Dongwook Lee, Youngho Cho +2 more
top venuehot direction
Abstract · Accepted to EMNLP 2026 (Main Conference). Demo: https://saga1214.github.io/PhraseLocalizedLCG/

Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to be spoken with the primary language's accent rather than its native one. We propose Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech. LCG replaces the single language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own language. To choose where to apply this localized guidance, we propose a self-attention probing technique that finds the phrase boundaries without external alignments. Together, these components generate speech in which each region carries the accent of its own language, requiring no fine-tuning or auxiliary models. Across diverse language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness.

0.81
12

Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization

cs.CL ·2026-09-01 ·Yixuan Wang, Freda Shi, Kanishka Misra
top venuehot direction
Abstract · Accepted to EMNLP 2026 Main

How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that describe indirect negative evidence against overgeneralizations: preemption (which privileges exposure to near-synonymous construction---e.g., she made him laugh) vs. entrenchment (all exposures to a verb's grammatical usages, including cases like He laughed). We disentangle these hypotheses by running controlled rearing experiments on LMs trained on child-caregiver conversations, where we systematically remove preemptive vs. non-preemptive evidence. We find that while LMs avoid overgeneralizations, they do not show preemption at a verb-specific level, instead showing weak but non-zero evidence of abstract preemption. Combined with results from analyzing the LMs' training dynamics, we find that LMs treat competing structures as indirect positive---as opposed to negative---evidence in the verb-specific condition. Insofar as preemption is the more plausible route to avoiding overgeneralizations in humans, our results point the need for there to be sensitivities to indirect negative evidence in neural network learners, and suggest new human experiments to test abstract preemption.

0.81
13

SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use

cs.AI ·2026-09-05 ·Zichen Tian, Jinpeng Chen, Cheng Gong, Suiyun Zhang, Rui Liu
top venuecode/data
Abstract · 23 pages, 3 figures, accepted by EMNLP 2026

High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-level dependencies that are critical to long-horizon tool use. As a result, even when a model selects the correct tool, task execution may still fail because the model fills tool arguments with fabricated, stale, or weakly grounded values. To address this problem, we propose \textbf{State-Guided Data Synthesis with Argument Provenance (SAP)}. SAP combines state guidance, tool-argument provenance constraints, and turn-level validation to efficiently construct tool-use trajectories with long-range dependencies and high accuracy. Using data generated by SAP, we build SAP-4B, which is highly competitive even when compared with much larger models across multiple benchmarks. Source code, synthesized data, and trained weights are available at https://github.com/Zichen1024/SAP.

0.80
14

Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation

cs.LG ·2026-09-01 ·Wentao Ye, Zhanming Shen, Zhiqing Xiao, Yao Ding, Haobo Wang +1 more
top venue
Abstract

Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is equally consequential. We study this choice through frozen-core adaptation: a calibration pass fixes left and right bases for each weight matrix, and fine-tuning optimizes only an $r\times r$ core. This removes the ability of trainable factors to repair a poor initial span and makes subspace quality directly observable. We introduce FCCA, which estimates the signed input--error cross-covariance, whitens it with diagonal Fisher moments, truncates it in the resulting local metric, maps the selected directions back, and applies thin QR to obtain stable core coordinates. Under a matched $r^2$ budget, we compare eight basis constructors on 11 tasks, four model settings, and three seeds. On Qwen2.5-3B, FCCA reaches an 83.0 macro-average, 2.3 points above the next-best matched-budget constructor, and exceeds its unwhitened RawGrad control on all 11 tasks. It ranks first at all three Qwen scales and finishes within 0.13 points of the best method on Llama-3.2-1B. Controlled ablations show gains of 2.7--17.2 points from whitening and identify QR as necessary for stable core optimization in the tested regime. Finally, FCCA comes within 0.32 and 0.23 average points of LoRA and DoRA while optimizing 36.9K rather than roughly 7.4M parameters. These results show that a carefully selected fixed span can recover most of the benefit of movable low-rank factors at a much smaller trainable and optimizer-state cost.

0.79
15

Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs

cs.LG cs.AI ·2026-08-31 ·Deokjae Lee, Sihun Chu, Hyun Oh Song
top venuecode/data
Abstract · EMNLP 2026 Long Paper - Main Conference

Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-induced quality loss under a fixed budget, but Mixture-of-Experts (MoE) models contain these layers in every expert of every MoE block, so the allocation space grows far larger than in a dense model. Existing methods either allocate within each block under a uniform per-block budget, or allocate across blocks through an additive proxy, and neither directly optimizes a model-level objective over the choices that couple the blocks. We propose Q-Strata, a bi-level allocator that ranks within-block assignments with a cheap proxy and allocates across blocks with a model-level objective evaluated on the assembled quantized model. Its inner stage caches a Pareto frontier of candidates per block over finely spaced budgets, leaving the outer stage to set one budget per block instead of a bitwidth for every linear layer. With the search reduced to one budget per block, the outer stage optimizes this model-level objective directly, capturing the inter-block coupling that additive proxies miss. On Mixtral-8x7B-Instruct, Qwen1.5-MoE-A2.7B, and DeepSeek-V2-Lite, Q-Strata consistently achieves lower WikiText2 perplexity than uniform-bitwidth GPTQ and the state-of-the-art MoE MPQ methods MxMoE and GEMQ in the low-bit regime. The code is available at https://github.com/snu-mllab/Q-Strata/tree/main.

0.79
16

Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving

cs.SE cs.DCcs.LG ·2026-09-04 ·Aditi Patodiya
publishedcode/datahighly cited
Abstract · v3: final accepted version, now published in IEEE Access (Early Access), DOI 10.1109/ACCESS.2026.3749922. Adds implementation scope and kern…

Major open-source serving stacks reuse the key-value tensors of a shared prefix by default. We measure what this prefix reuse costs in reproducibility. Holding model, decoding, seed and request order fixed at batch size one, we ran an eighty-episode multi-turn agentic tool-use workload with prefix reuse on and off across two engines and four weight formats. Without prefix reuse, repeated runs reproduced every token and log-probability in all ten configurations. With it, cache-hit and recompute paths diverged on both engines. On llama.cpp with GGUF weights this path divergence rises with quantization: for Qwen2.5-7B over ten independent server histories, it reached 37.4 percent of episodes at 16-bit and 82.5 percent at four-bit. Near-tie decisions became only about 1.2 times as common, while the cache-path change in top-two margins grew 4.9-fold from 16-bit to three-bit. Serving four-bit weights through 16-bit kernels left divergence not detectably different from 16-bit, placing the amplification mainly in the quantized execution path. At Q4_K_M, run-to-run divergence came mainly from llama.cpp's server-level prompt cache: under the canonical episode order it moved divergence by 37.5 points, and at its default, divergence spanned 20.0 to 28.7 percent under five random orders. With cache state restored, each path reproduced exactly while the two still differed. In the tested stacks, cached serving is irreproducible because the cache state is absent from the request and not reset by default. A single-turn bridge shows path divergence reaching task outcomes with no detectable net change in accuracy. We release the harness, logs, and analysis pipeline.

0.74
17

Leveraging Time-Causal State Variable Aggregation for Real-Time Schedule of Massive Air Conditioners

eess.SY ·2026-09-02 ·Jingguan Liu, Xiaomeng Ai, Shichang Cui, Xizhen Xue, Shengshi Wang +3 more
top venuehighly cited
Abstract · Published in: IEEE Transactions on Smart Grid (vol. 16, no. 3, pp. 2389-2403, 2025)

Air conditioner (AC) loads offer promising flexibility for active distribution networks to manage uncertainties, such as those in renewable energy generation, electricity prices, and load demand. However, real-time scheduling of ACs is challenging due to their massive temporal coupling constraints and time-causal uncertainties. To address this, a novel time-causal aggregation-based approximate dynamic programming (TCA-ADP) algorithm is proposed for efficient scheduling. The time-causality requirements for aggregating state variables are first analyzed to align with the real-time sequential decision-making process. Subsequently, an enhanced aggregation model is developed to ensure both high accuracy and adherence to time causality. The aggregation process is further reformulated as a linear program to optimize aggregation parameters and enable tractable computation. Accordingly, the TCA-ADP leverages aggregated state variables to approximate the value function as a new way, balancing computational efficiency and economy against the large value function space of massive ACs. By training the value function offline using historical data, the TCA-ADP efficiently achieves near-optimal real-time scheduling of massive ACs through parallel and closed-form disaggregation. Case studies demonstrate the effectiveness and scalability of the TCA-ADP, highlighting its aggregation accuracy, uncertainty handling, and the trade-off between economy and tractability.

0.74
18

Automating Static Code Analysis Through CI/CD Pipeline Integration

cs.CR cs.SE ·2026-09-01 ·Zachary Wadhams, Ann Marie Reinhold, Clemente Izurieta
top venuehighly cited
Abstract · 7 pages, 3 figures, published in 2024 IEEE International Conference on Software Analysis, Evolution and Reengineering - Companion (SANER-C),…

In the contemporary landscape of software devel-opment, securing sensitive data is paramount to safeguarding organizational reputation, preventing financial losses, and pro-tecting individuals from identity theft. This paper addresses the pervasive challenge of identifying and rectifying security vulnerabilities early in the development process, emphasizing the role of Static Application Security Testing (SAST) tools. While SAST tools play a crucial role in detecting vulnerabilities, widespread adoption has been hindered by usability issues, including high false positive rates and a lack of native pipeline support. This paper proposes a novel, generalized, and automated process for aggregating SAST tool outputs and integrating them into developers' familiar issue-tracking software. The process streamlines the identification and communication of security vulnerabilities during the development lifecycle, facilitating more efficient remediation efforts. We demonstrate the successful implementation of the proposed process with the SonarQube SAST tool in a GitLab-based development environment. Developers were positive about the structured implementation, real-time feedback, and proactive vulnerability management. However, despite some challenges such as a potential learning curve and tradeoffs between secure coding and workflow disruption, the overall positive impact on security awareness and responsiveness suggests that the proposed process holds promise in enhancing the security posture of software development practices

0.74
19

Clock-Gating Insertion Strategies on an Open-Source MSP430 Core: A Reproducible PPA Study and a Gate-Level Simulation Caveat

cs.AR ·2026-08-31 ·Xingran Huang, Qiming Guo, Jinwen Tang, Wenqi Jia, Dongzheng Wang
publishedcode/data
Abstract · 8 pages, 9 figures, 5 tables. Accepted for presentation at IEEE UEMCON 2026. Code and reproducibility artifact: https://github.com/yanyana11…

Clock gating, the standard technique for cutting dynamic power, is introduced either as hand-written behavioral clock gates at the register-transfer level (RTL) or as integrated clock-gating (ICG) cells inserted automatically during synthesis; the two are widely treated as interchangeable. In this paper we show, on a real open-source 16-bit microcontroller core (openMSP430) synthesized with a 32 nm standard-cell library, that they are not equivalent in practice: behavioral latch-based RTL gating is functionally correct in ideal RTL simulation (10/10 self-checking testcases, identical to the ungated baseline) yet fails at gate level: the gated multiplier result is never captured and reads zero, while tool-inserted ICG cells pass gate-level simulation cleanly (10/10). We root-cause the failure to a hold race introduced by the late latch+AND gated clock, and show it persists across eight simulation configurations including full Standard Delay Format (SDF) back-annotation, not a simulator-setting artifact. We then quantify the power/area/timing (PPA) impact of three gating strengths: RTL behavioral (Opt1), synthesis ICG (Opt2), and both (Opt3), against the ungated baseline, across four workloads and three process corners (ss/tt/ff). The benefit is corner-robust: ICG (Opt2) cuts dynamic power by 74-81% and total power by 25-30% at every corner. We also show that in this leakage-dominated 32 nm regime the total-power win comes from the area/leakage reduction that gating brings (leakage -24 to -30%), not from the large dynamic saving, which instead dominates active-mode energy. Our recommendation for low-power design on open-source cores is to prefer tool-inserted ICG cells over hand-written behavioral clock gates. The full flow (Design Compiler synthesis, PrimeTime PX power, and self-checking verification) is released as an open artifact.

0.73
20

A Nuclear-Norm Lower Bound for Dithered Scalar Quantization of Matrix Products

cs.IT cs.LGmath.NA ·2026-09-04 ·Piyush Sao, Narasinga Miniskar, Pedro Valero-Lara, Keita Teranishi, Sudip Seal
theorycode/data
Abstract · 17 pages, 2 figures. Code: https://github.com/piyush314/gauge-floors

We consider the problem of minimizing error in quantized matrix multiplication $C=AB$. Scalar quantization of the factors introduces rounding errors whose scale depends on the maximum absolute entries -- the ranges -- of their rows and columns. These ranges determine the quantization grid steps. To reduce the error, we optimize over product-preserving transformations that alter the factor ranges and grid steps without changing $C$. Specifically, we seek the smallest leading expected squared error over invertible inner changes of basis and orthogonal outer rotations. Under independent, zero-mean subtractive dither noise on an unbounded lattice, we prove the output-only bound $E_{\rm lead} \ge (c_A+c_B)/K \Vert AB\Vert_*^2$, where $K$ is the inner dimension, $c_A$ and $c_B$ are normalized noise variances, and $\Vert AB\Vert_*$ is the nuclear norm. The bound is tight: an SVD-aligned Hadamard construction attains the infimum whenever a Hadamard matrix of order $K$ exists, including every power of two, while an SVD-aligned DCT construction is within a factor of two for every $K$. Without outer rotations, Gram-matrix balancing minimizes factorization energy, and finite-set flattening achieves the bound within $C\log(K(m+n))$. For power-of-two $K$, conditional expectations deterministically select the Hadamard signs in $O((m+n)K^2)$ exact-real operations. Synthetic experiments verify both constructions and illustrate the tradeoff between regularization and conditioning. These results characterize the full-gauge optimum and quantify the cost of preserving row and column indices.

0.61