Found 2,471 document(s)
Page 56 of 165
-
Existing temporal video grounding (TVG) benchmarks primarily focus on localizing target video segments according to descriptive text queries of the visual content. However, real-world queries are more diverse and often r...
-
Learned humanoid controllers are usually trained in one simulator and then checked in a second one before they go near hardware. We ask what that check says about command delay. We train motion-tracking policies for a 24...
-
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing benchmarks focus on mode...
-
Max-pressure (MP) traffic signal control selects phases using pressure scores computed from estimated traffic states, but these states are uncertain and their consequences depend on whether they alter phase ranking and h...
-
High-fidelity Reynolds-averaged Navier--Stokes (RANS) simulations remain a standard tool for aerodynamic analysis, yet each solve on an unstructured mesh is computationally expensive, making many-query tasks such as desi...
-
Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop. Self-reflection, in which an agent critiques its output, is widely studied, yet a critique doe...
-
Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning ...
-
Music-driven group dance generation must decide not only how each dancer moves, but also what formation the group should form, when it should change, and who should execute each transition. Existing methods can generate ...
-
Robot manipulation involves localized changes: picking up a cup moves the cup while leaving the surrounding scene largely unchanged. Yet existing 3D visual pretraining methods, including recent dynamics-aware variants, m...
-
The recently discovered titanium-based kagome metal CsTi$_3$Bi$_5$, which exhibits superconductivity without an accompanying charge density wave, provides an ideal platform to investigate the intrinsic electronic structu...
-
Controlling scientific instruments requires parameters to be adjusted progressively in response to feedback from successive operations. When unobserved operating conditions evolve with operational history, responses beco...
-
Co-speech motion generation remains challenging over long horizons due to the need for temporal coherence and consistent style. Existing methods typically generate long motions segment by segment, either conditioning on ...
-
Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech. Comparatively little attention has been paid to analysing speech transcripts for L1 trace...
-
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that transfer information fr...
-
Existing RGBA generation methods commonly learn a transparency-specific representation through reconstruction, introducing an additional training stage and potentially altering the RGB decoding function inherited from pr...