Search papers, labs, and topics across Lattice.
100 papers published across 5 labs.
Coding agents can now be evaluated on tasks that truly test their problem-solving skills, rather than their ability to recall previously seen solutions.
Intent-based mutation testing reveals that over half of the generated mutations are unique, highlighting a new frontier in fault detection that traditional methods overlook.
Overcoming the challenge of over-merging, this methodology achieves a 99% AUC in identity resolution while drastically reducing mega-cluster sizes in the World of Code dataset.
Cross-lingual type representations can be extracted from untyped code, revealing hidden structures in state-of-the-art code models that challenge our understanding of their internal workings.
LLMs can generate diverse resident personas that produce executable smart home interaction schedules, eliminating the need for intrusive real-world data collection.
Cross-lingual type representations can be extracted from untyped code, revealing hidden structures in state-of-the-art code models that challenge our understanding of their internal workings.
LLMs can generate diverse resident personas that produce executable smart home interaction schedules, eliminating the need for intrusive real-world data collection.
Learning the generation order in multimodal tasks can boost performance by over 4%—a game changer for DLMs.
Procedural similarity can dramatically enhance repository-level code generation, achieving a 41.14% Pass@1 score that outstrips traditional methods.
AI-teacher collaboration outperforms imitation learning, boosting student performance by nearly 50% on challenging coding tasks.
CodeTracer can pinpoint the exact backdoor data responsible for unsafe code completions, even in the face of sophisticated attacks.
Unbounded loops in hybrid quantum programs can now be effectively analyzed for resource consumption and termination, filling a critical gap in quantum program verification.
Naive verification methods for PLCs can produce 44% false alarms due to unrealistic sensor models, but a new hardware-faithful approach eliminates these errors entirely.
XAlpha revolutionizes alpha discovery by turning it into a continuous learning process that adapts and evolves based on real-time feedback.
Strong execution in LLMs doesn't equate to effective educational control, as they struggle to lower cognitive demand despite being able to increase it.
Self-evolving LLM agents can slash latency by up to 62% while significantly boosting reliability in industrial applications.
Transforming LLM prototypes into auditable agents can ensure compliance and safety without sacrificing performance, achieving full utility in complex enterprise applications.
Aleena revolutionizes research software collaboration by ensuring that the rationale behind decisions is preserved across diverse communication channels.
LLM-generated skills fail to outperform basic task prompts in data science workflows, challenging the assumption that automated skill generation enhances AI performance.
Constrained decoding in diffusion models can boost accuracy by over 20% on complex tasks without significant latency penalties.
This AI assistant transforms how students grasp complex computational concepts by providing contextualized, example-driven learning without giving away answers.
SolSmith uncovered 25 hidden miscompilation bugs in the Solidity compiler, revealing critical vulnerabilities that could jeopardize smart contracts.
Personalization in AI-driven development can introduce significant biases, with age and gender influencing the very structure of generated code.
Achieving 99.94% of the theoretical maximum for entanglement certification reveals a new frontier in the efficiency of quantum software development.
Process features can triple the authorship attribution accuracy in educational programming contexts, revealing the limitations of relying solely on final code submissions.
SynapseFlow achieves over 4x higher branch coverage and uncovers critical bugs that other tools miss, revolutionizing fuzz harness generation.
TrajSpec transforms vague bug reports into actionable specifications, boosting APR success rates by over 18% through structured evidence gathering.
Existing benchmarks fail to reveal the true performance capabilities of LLMs, with only 6.11% showing significant speed advantages over traditional implementations.
Bug reports that work for humans can actually hinder AI agents, with localization cues being critical for repair success.
Overcoming the challenge of over-merging, this methodology achieves a 99% AUC in identity resolution while drastically reducing mega-cluster sizes in the World of Code dataset.
ATLAS automates the transition from high-level deep learning models to FPGA implementations, drastically reducing the manual effort required for custom hardware acceleration.
Optimization performance varies significantly by workload, challenging the notion that larger models are always superior in coding tasks.
Coding agents can now be evaluated on tasks that truly test their problem-solving skills, rather than their ability to recall previously seen solutions.
AI's role in code review is not a simple enhancement; it hinges on human expertise and the review process structure, revealing a complex interplay that challenges prevailing assumptions.
Trustworthy code generation can be achieved without post-generation adjustments, improving security and functionality simultaneously.
A staggering 65.8% energy reduction is possible with the right design strategy, but beware the "memory wall" that can obliterate those gains at scale.
fog enables a dramatic leap in motion recognition accuracy, allowing users to intuitively express complex emotions and movements in animations.
Coding agents struggle with native language tasks, achieving only 78.7% resolution in a benchmark designed to reflect real customer requests in Russian.
Knowledge Debt is a silent threat to developer expertise, but it can be mitigated by designing AI agents that actively promote incidental learning.
DebugTracker reveals that understanding the debugging process can significantly enhance educational assessments, moving beyond just final code quality to the intricacies of student reasoning and problem-solving.
Achieving a 24-bit watermark payload for code attribution without needing model access, this method outperforms existing techniques under multiple attack scenarios.
Automating cost function generation for steganography with LLMs can boost security and efficiency, achieving a 46.3% increase in execution speed.
Achieving 100% error detection accuracy in smart home configurations could revolutionize user experience and safety in automation systems.
Thoughtful feature curation reveals that structural code complexity is a far stronger predictor of deployment risk than traditional change volume metrics.
A new evaluation framework reveals that current assessments of LLM-powered agents often misrepresent their true capabilities in real-world software development.
A general LLM code agent can autonomously prove all targeted lemmas in software verification, achieving unprecedented coverage without expert intervention.
Grounding tests in a specification boosts LLM code correctness by 38 percentage points, revealing that content trumps quantity in test effectiveness.
Visual fidelity in web app generation doesn't guarantee functional interaction, as evidenced by a leading model scoring 7.5 on interaction inference while trailing others by over 5x.
Resolve rates mask critical insights about coding agent performance, but TraceProbe uncovers the hidden trajectory structures that explain why some runs succeed while others fail.
Clumping errors in author identity mapping can lead to a staggering misrepresentation of developer contributions, with previous maps inflating precision metrics by failing to account for conflated identities.
LLMs can accurately identify falsified software engineering definitions but paradoxically reject many correct ones, revealing a troubling bias in their understanding.
Reusing existing language models for software engineering texts significantly outperforms training new domain-specific models from scratch, challenging assumptions about domain adaptation strategies.
Modular task decomposition in AI-generated analyses boosts transparency and reliability, enabling smaller models to outperform larger counterparts.
RAG can reduce hallucinations in LLM-generated API code, but it risks introducing unnecessary parameters when endpoints are known.
Coding agents can generate observability artifacts, but they miss key diagnostic semantics, exposing fault signals for only 13.99% of failures.
HiFuzz outperforms traditional fuzzing techniques by leveraging hierarchical reinforcement learning to achieve deeper architectural state exploration and improved bug detection.
Evaluating code agents through their entire interaction trajectory reveals critical insights that traditional benchmarks overlook.
Agentic code review can transform AI-generated pull requests into high-quality solutions, outperforming traditional methods in both accuracy and usefulness.
Static metrics fall flat in predicting Java method energy usage, but adding execution time boosts accuracy significantly—up to 0.46 R2.
Fine-tuning for neural decompilation of Dart binaries fails to yield significant improvements, revealing critical pitfalls in current evaluation metrics.
Developers improved their prompt engineering skills significantly after just one hour with Prompt Coach, a tutor that adapts to their coding context.
Abliterated LLMs can dramatically enhance vulnerability detection and patch validation, achieving up to 67.8% usability in early-stage validation compared to just 29.9% for their aligned counterparts.
Students using text prompts outperformed their peers using voice input, highlighting the need for careful consideration of input modalities in programming education.
A staggering 69% to 98% failure rate in real denylist policy enforcement highlights a critical vulnerability in AI coding agents that remains largely unaddressed.
SCOPE's structured feedback mechanism boosts code generation accuracy, achieving a notable 39.4% pass rate on LiveCodeBench V6—outperforming existing methods by a significant margin.
AgentTether repairs over 65% of failures in complex LLM tasks without modifying the agent, revolutionizing how we ensure reliability in AI deployments.
VIC-RAGENT achieves up to 1.7x higher F1-scores in detecting vulnerability-inducing commits, revolutionizing how we approach software security.
Agent personality profiles can drive performance differences of over 11 percentage points in multi-agent software engineering tasks, revealing a critical design factor often overlooked.
AI coding assistants are reshaping open-source development by increasing contributor activity while simultaneously raising concerns about code maintainability.
Pharo-specialized LLMs achieve superior code completion accuracy, outperforming larger models and paving the way for robust support in low-resource programming languages.
PDEFlow automates the entire process from user input to solver-free inference, enabling rapid experimentation with complex differential equations.
OptiAgent not only automates the conversion of natural language into optimization models but also enhances transparency and self-correction, setting a new standard in the field.
AssemCAD transforms the landscape of CAD assembly generation by ensuring that mechanical assemblies are not only generated but also validated against engineering principles, achieving unprecedented levels of physical consistency.
MAST achieves superior precision in predicting test maintenance needs, outperforming state-of-the-art methods while revealing the intricate relationships between production and test code.
Even the best multimodal models struggle to reconstruct complex interactive dashboards, revealing a critical gap in current capabilities.
Observation-Aligned supervision reveals that traditional chart-to-code training often leads to hallucinations, and aligning targets with identifiable quantities can dramatically improve model performance.
LLM-driven program synthesis can automate EEG feature engineering while ensuring interpretability and high detection accuracy.
Most gains in LLM-based repair loops come from just the first three iterations, challenging the assumption that more iterations always lead to better results.
Evolved prompt transformation rules can fix 10-30% of LLM code generation failures, outperforming traditional execution-feedback methods.
Faulty code can bias LLM-generated tests, reducing fault detection effectiveness by nearly half when tests are generated after the code.
Intent-based mutation testing reveals that over half of the generated mutations are unique, highlighting a new frontier in fault detection that traditional methods overlook.
QuTuner achieves unprecedented efficiency in quantum compiler optimization, cutting tuning time by over 70% while dramatically improving circuit fidelity.
Energy-aware code generation can outperform human experts in efficiency, revealing that traditional performance metrics often mislead developers.
Source-guided neural network modifications can boost model accuracy by over 56% compared to traditional methods, demonstrating the power of LLM adaptation in model improvement.
Novice programmers often overlook crucial details in prompts, leading to a reliance on AI that can hinder their debugging skills and understanding of code generation.
Deliberately injecting bugs into GenAI-generated code significantly enhances students' debugging skills and success rates in subsequent attempts.
RustMizan exposes critical weaknesses in vulnerability detection, revealing that even advanced models struggle with line localization despite decent binary classification performance.
Coding agents can predict the correctness of code changes up to 25 steps in advance, revealing a latent programming horizon that challenges our understanding of their internal reasoning processes.
AI coding agents exhibit a surprising focus on name modifications and object creations, reshaping our understanding of their mutation strategies in performance optimization.
Higher AI autonomy in software development can cut effort and enhance adherence to requirements, but it may also raise developer frustration levels.
Tailoring AI agents to specific software engineering contexts can significantly enhance their effectiveness in hybrid teams, bridging the gap between human and machine collaboration.
InvWeaver outperforms existing methods by solving 72 out of 82 multi-loop benchmark problems, showcasing a breakthrough in invariant synthesis for complex programs.
Semantic conflicts in LLMs can dramatically reduce execution correctness, revealing that misleading cues often dominate model outputs.
KAT-Coder-V2.5 outperforms existing models in agentic tool-use, showcasing a new paradigm for autonomous coding agents within executable environments.
Contract structure, not language, dictates the reliability of specifications generated by LLMs, revealing critical vulnerabilities in production systems.
Nearly 80% of AI-generated pull requests are submitted concurrently, raising critical questions about collaboration efficiency and merge conflicts in AI coding agents.
Fine-tuned lightweight LLMs can successfully generate Control Flow Graphs from incomplete or erroneous code, outperforming traditional methods.
CI/CD workflows are riddled with reliability issues, with over 434,000 anti-patterns identified across thousands of projects, highlighting the urgent need for improved observability and recommendations.
SpecCoder boosts the quality of executable specifications by up to 358% and turns them into active tools for reliable code verification and repair.
Capturing and optimizing LLM agent behavior can slash operational costs by over 90% while maintaining high accuracy, challenging assumptions about model capability.
Role-based multi-agent code generation narrows the gap between AI-generated and human-written code, but still leaves room for improvement.
Code LLMs can recognize incorrect instructions but still follow them, leading to irrecoverable semantic errors that defy traditional evaluation metrics.
Correctness checks can miss kernels that are functionally valid but over 300 times slower than optimized versions, highlighting a critical evaluation gap in GPU DSLs.
SEDCoT achieves a 12% improvement in translation accuracy over existing methods while enhancing the readability of COBOL code translations into C.
Version alignment in LLM-generated quantum code is a critical challenge, with only 0.02 to 0.85 success rates across different models and SDK versions.
