ETH Zurich

Achieving best-in-class energy efficiency of 39 pJ/b, this innovative detector redefines the capabilities of MU-MIMO-OFDM systems.

Communication costs for consensus protocols can skyrocket under certain adversarial structures, revealing surprising dependencies on termination requirements.

Achieving near state-of-the-art performance with a 22M encoder, DistillPath-KS16 runs over 25 times faster than its larger counterparts while retaining critical accuracy in pathology tasks.

Multi-valued Byzantine Agreement can now be achieved with dramatically reduced complexity, making large-scale distributed protocols more feasible.

GenRec achieves unparalleled reconstruction fidelity while enhancing perceptual quality in novel view synthesis by intelligently separating reconstruction from generation.

Financial reasoning accuracy plummets by up to 51% with deeper computations, revealing critical gaps in LLM capabilities.

Achieving state-of-the-art predictive performance while providing transparent explanations, GARLIC transforms how we handle missing data in ICU time series.

MT models show a troubling bias towards US content, with specialized models proving less robust across diverse locales.

GENCO achieves up to 85x speedups in optimal power flow analysis while maintaining higher feasibility and optimality than classical methods.

Pre-computed embeddings can outperform traditional supervised models in estimating global biomass, reshaping our approach to carbon stock monitoring.

SpineSegDiff not only matches the best in vertebral segmentation but also reveals critical insights into degenerative disc conditions through uncertainty mapping.

Adaptive sampling can cut human evaluation costs while boosting the accuracy of model rankings in NLP tasks.

Foundation model agents can achieve stable cooperation in social dilemmas by inferring behavioral similarities, defying classical game theory's expectations of mutual defection.

RAG-Stack uncovers quality-performance trade-offs in RAG systems, achieving up to 153% more effective configurations than current methods.

By refining VLM-derived reward signals with structural priors, SAFT transforms noisy feedback into a reliable guide for faster and more aligned policy learning.

Recursive interaction with time-series data enables TimeRLM to achieve unprecedented accuracy in anomaly localization, outperforming traditional models by a wide margin.

Offloading Parquet decoding to the network can nearly double query throughput, transforming cloud-native database performance.

Achieving a Wasserstein mixing time that scales with $\sqrt{d}/\varepsilon$ could revolutionize the efficiency of sampling algorithms in high-dimensional settings.

Disfluencies are not just noise; they carry crucial meaning that, when ignored, significantly degrades translation quality.

Navigating document structures with a stateful evidence approach boosts answer quality by nearly 8% in complex question answering tasks.

Bridging the gap between reinforcement learning and control theory could unlock new synergies in optimizing unknown dynamical systems.

A unified framework reveals that dexterous manipulation skills are variations of a shared task, enabling seamless chaining and robust performance across diverse objects and hand morphologies.

Evaluators using cESA can achieve more reliable translation quality assessments while cutting annotation time by leveraging shared context across multiple outputs.

VidMap achieves unprecedented robustness and accuracy in metric reconstruction from uncalibrated videos, outperforming both SLAM and SfM methods under extreme conditions.

Finite precision in transformers can drastically alter memory operations, revealing a surprising hierarchy of expressivity based on attention mechanisms.

Tripody's innovative overconstrained design achieves 454% higher torsional stiffness at maximum height, revolutionizing lightweight construction robotics.

MLLMs can encode visual evidence but often fail to control their reliance on it, revealing a critical bottleneck in multimodal reasoning.

DVPSFormer reduces the computational burden of depth-aware video panoptic segmentation, enabling real-time decision-making for autonomous vehicles without sacrificing accuracy.

Resilience isn't just about bouncing back; it’s an emergent property shaped by the interplay of agents, with performance often undermining long-term stability.

Suppressing two-body losses by orders of magnitude opens the door to exploring itinerant quantum magnetism and novel quantum droplets in polar molecule systems.

Early design choices in the mapping pipeline can silently propagate errors, jeopardizing the reliability of large-scale geospatial maps.

GNM redefines the landscape of head modeling by integrating intricate anatomical details, achieving superior geometric fidelity that existing models overlook.

Achieving state-of-the-art hair dynamics in head avatars, DynHair allows for realistic and controllable hair movement that adapts to head motion.

Skill-SP not only pushes the performance ceiling of LLMs but also transforms initially misaligned models into high-performing agents through dynamic skill evolution.

Surprisal theory's reliance on language models leads to tautological predictions, undermining its empirical validity in psycholinguistics.

Constant-size post-quantum quorum signatures are finally achievable, revolutionizing Byzantine fault tolerance in distributed systems.

LLMs are not just passive observers; they can uncover novel cryptographic vulnerabilities that challenge our current understanding of digital security.

Larger LLMs may ignore user context more than smaller models, revealing critical insights into how linguistic framing can sway model responses.

NeuralChaos achieves optimal approximation rates for square-integrable processes using significantly fewer evaluations than traditional methods, reshaping the landscape of stochastic modeling.

Real-time adaptive encoding in a low-power AFE can revolutionize wireless neural signal processing for brain-computer interfaces.

Achieving a 1.6x speedup and 50% reduction in memory usage for CNNs on nano-drones could redefine their operational efficiency and application scope.

Training dynamics of Transformers can be reduced to a low-dimensional manifold, revealing how inductive reasoning emerges from data statistics and model initialization.

Temperature sampling can enhance mode diversity in diffusion models without sacrificing sample quality, thanks to a novel variance-corrective technique.

Achieving 205× latency reduction in FPGA-based neural networks could redefine the benchmarks for ultra-fast inference in latency-critical applications.

ARDY achieves real-time, controllable 3D human motion generation that outperforms existing methods in both fidelity and flexibility.

SBR reduces cognitive fatigue while achieving a 54.1% task success rate, outperforming traditional methods in real-time kinematic retargeting.

Scattering networks can achieve optimal separation capacity by strategically tuning filter frequencies and ensuring well-conditioned geometric couplings.

Only 2-4 principal components can capture 95% of the variance in the solution space of the Burgers equation, revealing a striking effective dimensional reduction.

A dual-$\boldsymbol k$-mesh strategy transforms BSE calculations, achieving unprecedented accuracy and efficiency in modeling absorption spectra.

A single minimal infinite-state tool can elevate finite-precision models to Turing completeness, while finite-state tools add virtually no expressivity.

Continuous severity scoring outperforms traditional multi-class classification in assessing lumbar spine degeneration, revealing finer distinctions in MRI evaluations.

Web agents can now safely interact with complex environments while avoiding prompt injection attacks by masking untrusted content without ever reading it.

LangLoc achieves unprecedented accuracy in indoor localization from natural language, closing the gap between coarse scene retrieval and precise pose estimation.

The learning rate is redefined as a structural parameter of training dynamics, fundamentally shaping the representations selected by gradient descent.

For the first time, a spectral sparsification algorithm achieves efficiency without reliance on approximation accuracy, revolutionizing parallel graph processing.

Integrating GNSS-derived Zenith Wet Delay into weather models boosts severe precipitation forecasts by nearly 9%.

Retaining past knowledge can actually impede real-time adaptation in dynamic environments, leading to a new framework for optimizing continual learning.

The Oracle Distance theorem reveals that all noising processes achieve the same optimal negative ELBO, linking diverse loss functions in diffusion models.

Segmentation masks can bridge the sim-to-real gap, enabling robots to achieve precise control over 23 degrees of freedom in dexterous manipulation tasks.

Synthetic sound effects can fool listeners into mistaking them for real recordings nearly 29% of the time, but a generator-specific detector can perfectly distinguish the two.

Achieving top rankings in a competitive setting, this work reveals how hierarchical soft-label learning can significantly enhance multimodal sexism detection in memes.

LIME turns ordinary egocentric video into a powerful tool for robots to dynamically adjust their camera poses based on user intent, revolutionizing how we think about robotic perception.

AEW achieves optimal performance in expectation for model selection aggregation, revealing a critical phase transition that could redefine its application in statistical learning.

Refining Cover's theory reveals that low-dimensional data structures can dramatically enhance classification capabilities, challenging traditional assumptions in machine learning.

SuperFlex achieves unprecedented reconstruction accuracy for 3D point clouds by enabling deformable superquadrics to represent complex geometries robustly.

Preemptive VCs can slash link resource usage by 76% while maintaining comparable performance in deadlock-free AXI4 NoCs.

Category theory reveals that AI identity is not a simple equality of trustworthiness but a complex interplay of transformations and histories.

Resonant modifications of London dispersion interactions can significantly enhance reaction rates in molecular systems under vibrational strong coupling.

RAISE keeps LLM-based heuristics resilient, outperforming traditional methods by up to 19 times under real-world distribution shifts.

JETO-Mine uncovers a staggering 660 execution time improvement patches in Java, revealing a critical lack of performance testing in open-source projects.

AugSplat boosts reconstruction quality in sparse-view 3D vision by leveraging synthetic views from neural radiance fields, achieving real-time performance without sacrificing accuracy.

NeuReasoner reveals that while LLMs can excel in certain reasoning tasks, they still falter in critical areas like decision-making under uncertainty, challenging previous assumptions about their capabilities.

Factorizable Normalizing Flows enable efficient modeling of complex parameter-dependent densities without the combinatorial explosion of sampling joint configurations.

GRAINS achieves up to 47.8x speedup in genome graph analysis by processing data directly within storage, revolutionizing efficiency in genomic research.

Achieving accurate pose estimation with rolling shutter cameras using just seven correspondences could revolutionize real-time applications in consumer devices.

Mixing rates improve by 1.5-3 times with the new SA-PAL method, showcasing a dramatic leap in sampling efficiency for complex systems.

AI-assisted LCA interpretation can now translate complex environmental data into actionable strategies, reducing uncertainty in decision-making.

Learning a truncated Gaussian can be done in optimal time and sample complexity without the usual computational overhead of gradient descent.

Achieving 51% higher throughput with low-precision arithmetic while maintaining accuracy could redefine efficiency benchmarks in semiconductor simulations.

Vehicle chassis shadows can be transformed into a powerful cue for accurately reconstructing the 3D geometry of nearby objects, even in challenging conditions.

Achieving a 12-cycle interrupt latency, CVA6-RT rivals simpler microcontrollers while delivering superior performance for mixed-criticality applications.

EmuGEMM achieves up to 5.5x speedup over cuBLAS ZGEMM while maintaining accuracy, revolutionizing low-precision matrix multiplication on modern GPUs.

Quantum back-action can dynamically create excitonic states, challenging the conventional understanding of excitonic behavior in semiconductors.

Optimization-guided diffusion not only ensures feasibility in robot control tasks but also enhances task success rates by up to 23 percentage points without retraining the model.

Kops enables significant performance improvements in eBPF by allowing new operations to be added without compromising kernel safety or increasing the trusted computing base.

The effectiveness of antidistillation defenses hinges on the threat model used, revealing that current defenses may offer a false sense of security.

Language-adaptive tokenization can significantly enhance morphological alignment without the need for separate vocabularies for each language.

Achieving accurate cosmological inference with just 60 high-fidelity simulations could revolutionize the cost-effectiveness of weak lensing studies.

Clutch achieves up to 12x throughput improvement for vector-scalar comparisons in DRAM, revolutionizing data-intensive workloads.

Writing to DRAM rows twice can significantly enhance their reliability, reducing bitline failures by over 30% in critical operations.

A unified framework that combines knowledge graphs and question generation could revolutionize how AI systems retrieve and reason about information.

Conventional computing systems are ill-equipped to handle the explosive growth of biological data, necessitating a paradigm shift in computer architecture for healthcare applications.

ColumnKeeper mitigates a new class of DRAM vulnerabilities with less than 3% performance overhead, paving the way for more resilient memory architectures.

Multi4D achieves state-of-the-art rendering quality and segmentation accuracy by dynamically allocating modeling capacity across multiple structured levels, revolutionizing how we handle dynamic 3D representations.

TD learning can achieve variance bounds comparable to Monte Carlo methods, but with the added advantage of shorter updates leading to more stable estimates.

CoT transformers can simulate Word RAM algorithms with poly-logarithmic overhead, revolutionizing our understanding of their computational efficiency.

Sparse annotations can yield results nearly indistinguishable from dense ones, with SA-VIS achieving over 1% improvement in AP on state-of-the-art benchmarks.

Action-aligned representations can be achieved without complex training methods, enabling robust planning in dynamic environments.

Interactive candidate selection in bioprocess optimization reveals trade-offs between performance, uncertainty, and robustness, empowering experts to refine criteria as models evolve.

PuDGhost reveals that interference from neighboring DRAM cells can compromise computation accuracy in Processing-using-DRAM operations by nearly 50%.