Found 42,749 document(s)
Page 23 of 2850
-
Photo Response Non-Uniformity (PRNU) is widely regarded as the most reliable marker for source camera identification. Recent studies, however, report high correlations between images and fingerprints from different moder...
-
Building and expanding access to digital archives supports language reclamation and creates lasting resources for community revitalization. Designing effective tools to support these efforts requires taking into account ...
-
Classical robot control, Finite State Machines and Behavior Trees (BTs), is deterministic and inspectable but fixed at design time: it fails on situations its designers did not anticipate. Foundation models can synthesiz...
-
We present experimental evidence suggesting that information about whether a model's reasoning is on the right track can be linearly decodable without defining a causally useful direction for steering. To study this, we ...
-
Recent advances in artificial intelligence have contributed to several information-theoretic results through genuinely different modes: a language model may suggest a proof, participate in an extended mathematical dialog...
-
Supervised fine-tuning treats the expert demonstration or gold response as a one-hot target, suppressing valid alternative continuations that the model would otherwise assign probability to. We propose Gold-Conditioned D...
-
Wiring and bandwidth bottlenecks between a quantum processor and room-temperature electronics can be reduced by placing digital control at the cryogenic stage, but commercial foundry standard-cell libraries are not speci...
-
Alan Turing proposed constructing a ``child machine'' and educating it rather than directly programming an adult-like intelligent machine. Recent work on model raising revives this developmental view for Large Language M...
-
Continuous-time generative models, from diffusion models, flow matching, and now flow maps, owe their practical value to high-fidelity generation and steerability. In many applications, a ground-truth latent ``oracle'' r...
-
Previous work has argued that multilingual LLMs encode language-specific features most strongly in their initial and final layers, implying that intermediate layers support language-agnostic representations. This paper r...
-
We study a natural synchronous greedy matching process in ErdΕs-RΓ©nyi random graphs $\mathbb{G}(n,p)$ and give a rigorous analysis of this parallel stochastic dynamics. The process evolves as follows: in each round, ever...
-
We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initialization. One solution class consists of solutions...
-
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changing energy cost of inference under GPU contention. ...
-
We give the first unconditional family of polynomial-time algorithms that breaks the $1/3$ approximation barrier for symmetric bimatrix games. For every fixed $Ξ΄>0$, an algorithm in this family computes a symmetric $(1-1...
-
Determining OpenCL channel depths for Decoupled Access-Execute (DAE) architectures in High-Level Synthesis (HLS) is critical for balancing performance and hardware efficiency. Conventional static analysis tools often ove...