Skip to main content
Search

The University of Texas at Dallas

5 related articles

Subscribe to updates
  1. A weak judge's taste is readable before training: the probe named Africa, and all 128 final answers said it

    Language models are often trained against a learned judge instead of the truth, but what that judge rewards could previously be seen only after training, from the policy's behavior. Three judges were trained from a 1B-parameter model on 500, 2,000 and 8,000 labeled answers, and a single-edit probe measured each judge's lift on wrong answers before any training. The probe predicted a climb onto flagged text against the weakest judge; after training, 115 of 128 final responses were one Sahara sentence ending "Answer: Africa", and the judge's mean score rose from 0.20 to 0.82. Against the strongest judge it predicted nothing climbable, and that run was not exploited.

  2. arXiv

    EDiS decomposes a graph once into cacheable edge-disjoint subgraphs and tops 19 node-classification benchmarks at matched edge budgets

    EDiS separates one-time structural extraction from per-epoch graph composition: it decomposes the graph once into cacheable edge-disjoint subgraphs using feature-based scores and successive maximum-score covering forests, then recombines them into training graphs under edge-budget constraints without re-extracting structure; across 19 homophilic, heterophilic, and large-scale node-classification benchmarks at the same edge budget against 17 baselines, EDiS-Lite achieves the highest mean benchmark score and the lowest average rank and gap-to-best.

  3. arXiv

    A survey unifies joint, cross-modal and joint-editing video-audio generation on one distribution and gives the first systematic taxonomy of joint audio-visual editing: nine categories, 28 edit types

    Observing that video and audio are perceived together yet most generative models treat them in isolation, this survey casts joint generation, cross-modal generation (one modality from the other) and joint editing as three problems defined on a single distribution over audio-visual pairs, organizes the field around one question—how the output is kept coherent across modalities in time and semantics—proposes a taxonomy along five design axes (generation strategy, audio representation, video representation, alignment enforcement, pretraining reuse), and, to the authors' knowledge, provides the first systematic taxonomy of joint audio-visual editing, mapped as nine edit categories spanning 28 edit types, together with methods, datasets and metrics for each setting and a closing list of open pr

  4. arXiv

    Jev-Mem puts a System-One control plane over agentic memory, lifting LoCoMo overall score to 0.777 while cutting memory build time to 158 seconds

    Jev-Mem introduces an agentic memory architecture inspired by System-One/System-Two cognition, in which a dedicated System-One control plane handles memory typing, relation construction, query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping, while System Two is reserved for complex reasoning and answer synthesis; on LoCoMo it reaches an overall LLM-as-a-Judge score of 0.777 (an 11.0% relative gain over the strongest baseline), a memory construction time of 158 seconds (a 6.6 speedup over the fastest competing memory system), and an average query latency of 0.93 seconds (a 36.7% reduction).

  5. RNA

    A Continuum-Based Reaction-Diffusion Model Reveals Spatial Spread of Gene Silencing in Chromosomal Inactivation

    This work develops a continuum-based reaction-diffusion model of XIST-mediated gene silencing spread on chromosomes, finding that XIST spread can be tuned by known negative feedback loops regulating its synthesis and degradation, while silencing spread is controlled by a wave-pinning mechanism driven by global regulation of the silencing complex together with local epigenetic regulators, and uses a 3D chromosome structure inferred from experimental data to show spatiotemporal regulation of silencing spread.

You’re all caught up