research note
UniPool addresses a structural inefficiency in standard Mixture-of-Experts (MoE) transformers: the rigid convention that each transformer layer owns its own private set of expert FFNs, which forces…
research note
UniSD addresses a core tension in LLM post-training: how to improve a model using only its own outputs as supervision, without access to a stronger external teacher
research note
The paper addresses a core bottleneck in LLM self-improvement: the inability to reliably generate novel, *valid*, and *hard* mathematical problems without human experts
research note
This paper addresses a key practical challenge in astrophysical population inference: how to incorporate follow-up observations when the process deciding which initial survey detections are selecte…
research note
This poster paper tackles the absence of a principled, quantitative definition of 'low-resource language' within the Linked Open Data (LOD) / Semantic Web ecosystem
research note
This paper attacks a foundational assumption underlying LLM leaderboards like Arena (formerly LMArena): that a single global Bradley-Terry (BT) ranking meaningfully summarizes user preferences acro…
research note
This paper addresses the practical and policy gap in online age verification — specifically, how to reliably prevent minors from accessing harmful content (pornography, gambling, violence, alcohol)…
research note
SLYP targets a very specific and nasty class of Windows local-privilege-escalation bugs: race conditions in COM services that run privileged, are reachable from authenticated users, and often expos…
research note
AllSERP is a dataset enrichment layer built on top of AdSERP (Latifzadeh et al., SIGIR 2025), the only public IR dataset combining eye gaze, cursor, scroll, pupil, and click telemetry against groun…
research note
This paper asks a practical question for misinformation screening: if you give non-expert crowd workers short audiovisual clips, how reliably can they tell authentic media from deepfakes, and if th…
research note
The authors designed a recovery evaluation rubric with three dimensions—Recovery Quality, Tone Alignment, and Appropriateness—and nine sub-dimensions, to assess chatbot recovery responses
research note
This paper addresses the tension between capability, cost, and privacy in LLM-based personal agents
